Founding Engineer at Verse · Bengaluru (Bangalore) · 2 - 5 years · ₹15L - ₹20L / yr (ESOP available) · Bootstrapped · Posted 17 May 2026

Founding Engineer (Bangalore)
The problem:
Business enterprises overpay vendors - on every batch of invoices, on every month because the data that would catch lives in different systems. We are building an AI agent that processes invoices end-to-end, reasons across all the relevant sources, flags genuine discrepancies, and acts - without a human having to investigate each one.
What you will own
Everything engineering. Schema design to deployment to the 2am fix when something breaks in production. There is no tech lead above you. There is no platform team. There is the architecture, you, and the founders. Concretely, this means building:
- A multi-stage agentic pipeline that takes a vendor invoice and produces a structured decision - fully autonomous for clear cases, escalating to human review for genuinely ambiguous ones. We use LangGraph, but if you've built equivalent systems with Temporal, Prefect, or custom state machines with LLM orchestration, that works
- An LLM-powered extraction layer that handles real invoices - scanned PDFs, stamped documents, inconsistent layouts - and returns structured output
- A graph data model that connects invoices to various sources and can traverse those relationships to detect discrepancies
- ERP connectors, GST validation logic, and a write-back layer that closes the loop
What we need
- Strong Python. Async FastAPI, clean service boundaries, tests that actually catch bugs. You have shipped Python backends that handled real production load
- Solid Postgres. Complex queries, schema design, migrations without downtime, row-level security for multi-tenant data. pgvector is a plus - if not, you pick it up fast
- LLM API experience in production. You have called an LLM API for something that real users depended on. You know about structured output, retry logic, cost management, prompt versioning. A side project counts if it was genuinely deployed
- Comfort with graph data models. You understand when a graph is the right structure and when it is not. You do not need deep Neo4j production experience - you need to understand graph relationships conceptually and be willing to learn Cypher. It is a 2-day ramp for the right person
- Working knowledge of deployment. Deployed and operated production workloads on GCP. Cloud Run, Cloud SQL, Cloud Storage, Redis — you're comfortable across the stack. If you've done it on AWS, the translation isn't hard, but GCP is where we are
- You own things. Not "I contributed to" - you designed it, shipped it, and fixed it when it broke. That pattern needs to be visible in your history
Good to have, not mandatory
- Built an agentic pipeline with multiple stages
- Any fintech, P2P domain experience - even tangential
- Worked at a startup with under 20 people
- Has a GitHub, blog, or writeup that shows how you think about a hard technical problem
What you get
- The hardest engineering problem you would have worked on. This is not CRUD with an LLM bolted on
- Real ownership. First engineering hire. Your architectural decisions will be in this product five years from now
- Equity that matters. ESOP - Open to discussion. We are pre-seed - this is a bet, not a guarantee. We will not pretend otherwise
- No meetings tax. You work directly with the founders. The product is specified clearly. You know what you are building and why
Honest about stage: We do not have a production ready infra yet. We have a complete architecture specification and a working prototype. If you need the stability of an established engineering org, this is not the right moment. If you want to build something real from zero and own a meaningful piece of it, it is.
The founders
One of us has spent 20 years building revenue and operational engines at companies where there was no playbook - part of the pilot team that established the world's largest search company's direct sales operations in India, managed global operations for a global mobile advertising platform, scaled a B2C platform to become one of India’s leading edtech platforms and most recently worked on building an enterprise Agentic Voice AI platform. The other has spent 15 years taking AI from demo to production in domains where failure is expensive - voice, lending, and conversational systems across a Series D conversational AI company, a major telco, a Big 4, and a leading NBFC.
Two IIT/IIM alumni who have both watched AI work in enterprise, and know exactly what it takes to get it there. We are not building this product because it sounds interesting. We are building it because we have both sat across the table from CFOs who know they are losing margin and have no tool capable of doing anything about it.

About Verse
About
Company social profiles
Similar jobs (10)
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
Role Overview
We are looking for a strong Senior Python Engineer with hands-on AI/ML and Automation experience to join
our engineering team.
The engineer will work on high-scale backend systems, intelligent automation platforms, OCR/document
processing, AI-powered workflows, browser automation and integrations across multiple products.
This is not a role for someone whose AI experience is limited to calling LLM APIs. We need an engineer who
understands Python deeply and has built, deployed and maintained real production systems.
Experience Requirements
l Minimum 4 years of professional software development experience, primarily using Python.
l Minimum 2 years of practical hands-on experience in AI/ML, intelligent automation or closely related production
systems.
l Candidates with 4-6+ years of strong relevant experience are preferred.
l Strong production/backend engineering experience is essential.
Core Python & Backend Skills
l Python; FastAPI / Django / Flask; REST APIs and backend service development.
l Async programming and concurrency; multithreading / multiprocessing where appropriate.
l PostgreSQL / MySQL; Redis; background jobs and task queues such as Celery.
l WebSockets / real-time communication where required; authentication and authorization; API integrations.
l Docker; Linux; Git; logging, debugging and production troubleshooting.
l Ability to build fast, reliable and scalable Python services rather than only scripts.
AI / ML Requirements
l Machine Learning fundamentals; model training, evaluation and inference; data preprocessing and feature
engineering.
l Scikit-learn; PyTorch or TensorFlow; NLP.
l Embeddings, semantic search and vector databases.
l LLM integrations, prompt engineering, structured output and tool/function calling.
l RAG pipelines; AI agents / agentic workflows.
l OpenAI, Gemini, Claude or equivalent integrations; local/open-source model integration where appropriate.
l Understanding of model selection, accuracy, latency and cost trade-offs.
Automation Engineering
l Playwright; Puppeteer or equivalent browser automation frameworks; Selenium where appropriate.
l Headless browser and web workflow automation; form/repetitive task automation.
l Session/cookie management; file upload/download automation; API + browser hybrid automation.
l Retry and recovery mechanisms; scheduling and background execution.
l Queue-based automation workers; parallel/concurrent task processing.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
AI / Backend Engineer — Remote (India / Overseas)
Company: Ink'd
Compensation: $1,500–$2,500 USD/month, depending on experience
Type: Independent contractor, long-term opportunity
Ink'd is building a voice-first AI platform for residential real estate transactions. Our AI assistant allows real estate agents to generate contracts, automate workflows, and complete transaction documentation through natural conversation.
We're looking for a highly capable AI/backend engineer to help scale and maintain our production platform.
Responsibilities
- Build and maintain production AI agent workflows
- Develop integrations with third-party APIs and services
- Work with LLMs, structured data extraction, and document generation
- Troubleshoot production systems and improve reliability
- Build scalable backend services and maintain databases
- Collaborate directly with the founder and engineering team
Technical experience
- Python, FastAPI, Node.js, and REST APIs
- LLM APIs, tool calling, and agent orchestration
- PostgreSQL and cloud infrastructure
- GitHub, CI/CD, debugging, and deployment
- Experience with voice AI, WebSockets, or document processing is a major plus
What we're looking for
Someone who has independently shipped production software, can troubleshoot unfamiliar systems, communicates clearly, and takes ownership of their work.
Please include your GitHub, two examples of production systems you've built, your specific contributions, monthly compensation expectations, and availability.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
We're hiring Drumbeat's first Senior Product Engineer to help us go to the next level.
We're not first-timers. We're the team that founded Phrasee in 2015 and grew it to more than 100 people, customers around the world, and a >$100m exit. Lots of people made lots of money, including the founding employees.
With Drumbeat, our plan is to do it all again… except this time, bigger and faster.
What is Drumbeat?
Drumbeat (www.drumbeat.com) predicts your next best action on LinkedIn, then copilots your team to turn invites, DMs and posts into pipeline.
We launched in September 2025 and have raised a £2m seed round led by a well-known VC. We're building the core team around our cofounders (Parry, Jonny and Dan) and Mohit, our Engineering Manager and Phrasee's first engineer. You'll report to Mohit.
What you'll be building on
- Setlist: a short, ordered list of the right things for each person to do today.
- Radar: predicts who each rep should connect with now, not everybody who matches a job-title search.
- Riff and AuthorDNA: help people find something worth saying, and write it in their own voice.
- Campaigns, Conversations, Backstage and Analytics: team-wide activity, replies, company knowledge and reporting.
Under the hood: Django and PostgreSQL, background jobs on Redis, LLM workflows, statistical models that learn what works, and integrations with LinkedIn and CRMs. A lot of our code is written with AI coding agents, inside a strict engineering process.
How we think about engineering
- "Human-first AI, not AI-first humans." AI agents write a lot of our code. They don't make our decisions. We want someone super smart without AI, and even smarter with it, who knows when the machine is blowing smoke.
- "Spend 55 minutes on the problem." Understand what's actually wrong before you fix it.
- "Fix the class, not the instance." Every bug is an example of something bigger. Find the pattern, and fix it everywhere it lives.
- "A check must be able to fail." A test you've never seen go red proves nothing.
- "You don't need a Ferrari to drive to the supermarket." Simplicity over cleverness, every time.
What you'll own
- Technical architecture. How Drumbeat is built, so it holds up as we add customers, features and integrations.
- Shipping features end to end. From Parry and Mohit's briefs, and turning Parry's MVPs into production features.
- Foundations. Scale, resilience (safe retries, timeouts and fallbacks when outside services wobble), cost and refactoring.
- What you build. Once it's live, it's yours: you maintain it and fix it.
- The hardest bugs. The ones nobody else can crack.
Your experience
- 8+ years as an engineer, at a product company, preferably B2B SaaS.
- Time at a smaller company, so you know how to get stuck in.
- You've owned a system in production, not just added features to one.
- Senior Python and Django: Postgres, background jobs, correctness in production.
- System architecture and refactoring.
- You direct AI coding agents well, and explain trade-offs in plain English to people who aren't engineers.
Where you'll work
Delhi / NCR. You'll be in our Delhi office some days each week, alongside Mohit.
Pay
₹40–65 lakh CTC, plus equity that vests as the company hits revenue milestones.
This is probably not a job for most people. Don't apply if you want an easy job. Apply if you want a hard one: lots of responsibility, very little bureaucracy, plenty to figure out, and a genuine chance to shape what this company becomes… and make a bunch of money as a result.
If that sounds exciting, LET'S PARTY.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
Key Skills :
• Builds AI-powered business applications end to end, from the Python/FastAPI service layer through
to React-based user interfaces, deployed on Databricks
• Designs and builds APIs connecting AI agents, governed data and user-facing workflows, including
decision capture, audit logging and file exports for downstream systems
• Codes rule-based decision engines in Python (e.g. allocation or replenishment logic) that work
alongside ML models
• Integrates LLM agent runtimes into applications, including tool calls, streamed responses and cited
outputs
• Writes performant SQL against governed data and ensures services operate within defined access
boundaries
• Builds interactive screens, dashboards and conversational interfaces that let users review and act
on AI recommendations
• Works closely with GenAI/ML engineers, data engineers and BA
Only immediate joiners are considered.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
About Juicelabs
Where creative engineering meets applied AI.
We build vertical, AI-native tools that unlock fresh insights and creative superpowers for clients in advertising, ecommerce, and beyond. We're a nimble team of founders and builders obsessed with using AI to solve real problems in ways that didn't exist eighteen months ago.
The Opportunity
A year ago, we would have posted this as a backend role. That role doesn't really exist any more.
Code has become nearly invisible. Agents write it, test it, and iterate on it faster than anyone could read it. What's left is the work above it: deciding what's worth building, designing systems that hold up at 10x, and building the setup that turns a clear spec into working software.
That's the job. At your level, it isn't one system. It's several workstreams, running at once.
You'll work directly with our Cofounder/CTO on products going from zero to one, with AI at the core of both what we build and how we build it. Real ownership, real scope, and an unusual amount of leverage: one engineer with good judgment and a well-tuned agent setup now ships what a small team used to.
What you'll do
- Own multiple workstreams in parallel. Two or three features of the same product moving at once, each with its own scope, edge cases, and failure modes. You decide where your attention goes this week, and nothing goes stale.
- Run a fleet, not a single agent. Design the setup that makes high-throughput work possible: how work gets broken down, specced, and run across many agents at once, so output scales without things breaking.
- Design the system. Service boundaries, data models, failure modes. Make the architectural calls before a line gets generated, and be able to explain the trade-off six months later.
- Write the spec. PRDs and technical designs are the new source code. A vague spec produces confidently wrong software, fast. Scope, edge cases, non-goals, what "done" means.
- Own it end to end. Ideation → design → build → deploy → monitor → iterate, including functional UX. Nobody hands you tickets.
- Set the workflow. Bring your harness: CLAUDE.md, AGENTS.md, subagents, custom commands, eval loops — whatever makes agents reliable rather than merely impressive. We want to steal your good ideas.
What we're looking for
- High agency. You see the gap and close it. You don't wait for direction, and you don't need to be chased for follow-through. This is the single trait we screen hardest for. And you can do it across several workstreams at once, without dropping threads.
- Real system design depth. You can reason about consistency, caching, queues, and scale — and about complexity, because you need to know when an elegant-looking solution is quietly quadratic. LeetCode ninja not required. Being able to explain why this won't blow up at 10x, very much required.
- Clear thinking, put to paper. You get the thinking straight first, then write it down so nobody has to guess: PRDs, design docs, PR comments. Writing is most of how you'll direct both humans and models, and muddy thinking on paper becomes muddy software.
- You've shipped to production. Deployed things, monitored them, been paged by them, fixed them. Docker, CI/CD, cloud infra. Our stack is mostly Python (FastAPI), Postgres, GCP/AWS — but we care more about how you think than which framework you've memorised.
- You orchestrate AI, not just use it. Not "I've tried Copilot," and not just "I use Claude Code." You've run multiple agents in parallel and developed opinions: how to split work so they don't step on each other, where they excel, where they confidently lie, how you structure a repo so they don't wander, and how you verify what comes back at volume.
- Startup energy. Multiple hats, fast cycles, and the judgment to balance "ship it now" against "will this survive contact with real users?"
Experience
3–6 years of professional experience (full-time positions, excluding internships).
Location / How to apply
On-site at our office in HSR Layout, Bangalore.
Apply through this posting, or email us with a link to the best thing you've built.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
About PortOne
PortOne is building the reconciliation and data intelligence layer for payments across Korea and international markets. We are a Series B startup backed by Softbank and Hanwa Capital, powering multi-billion dollars in annualised settlement volume for 2,000+ merchants across Korea, Thailand, Singapore, Indonesia, and beyond.
We are building AI-native products for leading brands — intelligent automation layers on top of complex financial data pipelines. If you want to work at the intersection of fintech, data engineering, and applied AI, this is your role.
Culture and Values
* You will be joining a team that stands for making a difference.
* You will be joining a culture that identifies more with Sports Teams rather than a 9 to 5 workplace.
* Your will have peers who are/have
** Highly Self Driven with A sense of purpose
** High Energy Levels - Building stuff is your sport
** Ownership - Solve customer problems end to end - Customer is your Boss
** Hunger to learn - Highly motivated to keep developing new tech skill sets
Your Work Ethic
* You are an athlete and building apps is your sport.
* Your passion drives you to learn and build stuff and not because your manager tells you to.
* You obsess over correctness — a bug in a settlement figure or a silent data drop is not acceptable to you.
* You have an eye for detail that most engineers skip past, and you take pride in getting it exactly right.
* Your work ethic is that of an athlete preparing for your next marathon. Your sport drives you and you like being in the zone.
* You are NOT a clockwatcher renting out your time, and NOT have an attitude of "I will do only what is asked for"
What will you do?
- Build and maintain financial data ingestion pipelines that pull settlement and transaction data from marketplace platforms (Amazon, Shopee, TikTok, Qoo10, Rakuten) on behalf of large brands operating across multiple Asian markets.
- Own reconciliation workflows end-to-end — from raw marketplace data to verified, merchant-ready settlement reports — ensuring every figure is correct and every discrepancy is surfaced, not swallowed.
- Design and implement AI-native features that automate financial analysis: agentic triage of settlement mismatches, root-cause detection across large transaction volumes, and intelligent alerting for ops and merchant teams.
- Instrument data quality and health monitoring so that silent failures — missing records, schema shifts, delayed ingestion — are caught before they reach the merchant.
- Build APIs and tooling that enable PortOne's ops and merchant success teams to investigate, verify, and close financial discrepancies faster and with more confidence.
- Expand platform coverage by integrating new marketplaces and new report types, working closely with data formats that are often inconsistent, undocumented, or changing without notice.
- Uphold rigorous engineering standards — correctness in financial data is not negotiable, and you treat edge cases and off-by-one errors with the same seriousness as a production incident.
- Uphold high engineering standards across codebases and processes.
- Collaborate with product, design, infrastructure, and operations stakeholders.
Skills and Experience
* Have ideally 4 to 6 Years of experience shipping high quality products/live features and workflows
*AI-native development — you build products where AI is a first-class component, not a bolt-on.
* Strong backend engineering foundation — Go (Preferred), Python, or equivalent; REST/gRPC APIs; database design.
* Understands how to build scalable, resilient, and observable distributed systems.
* Must have built data flows and applications end to end taking full ownership
Preferred Skills and Background
*Prior experience/built apps in golang backend
*Data and data engineering background — comfortable with data pipelines, ETL/ELT patterns, event-driven architectures, reconciliation logic, or analytical workloads.
*AI agentic development — experience building or working with agent frameworks, tool-use patterns, LLM orchestration, or automated reasoning pipelines.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
Job Title : Full-Stack AI Product Engineer
Experience : 3+ Years
Work Mode : Remote
Time Zone : IST
Engagement Type : Freelance
Availability : Must be comfortable attending US client calls during IST night hours.
Role Overview :
We are looking for a Full-Stack AI Product Engineer with hands-on experience building and deploying production-ready AI-powered applications. The ideal candidate should have strong Python backend development skills, practical expertise in LLMs, AI agents, RAG pipelines and tool calling, along with basic frontend development knowledge.
Mandatory Skills :
Python, FastAPI, AI / LLMs, AI Agents, RAG, Tool Calling, PostgreSQL, Redis, Docker, GCP / Cloud Run, CI/CD, Basic React.js / Next.js.
Key Responsibilities :
- Design, develop and maintain AI-powered products using Python and FastAPI.
- Build and integrate LLM-based applications, AI agents, RAG pipelines and tool-calling workflows.
- Develop scalable backend services and REST APIs.
- Work with PostgreSQL and Redis for data storage, caching and performance optimization.
- Containerize applications using Docker and deploy services on GCP, preferably Cloud Run.
- Implement CI/CD pipelines and follow production deployment best practices.
- Develop and integrate basic frontend features using React.js or Next.js.
- Troubleshoot production issues, optimize performance and ensure application reliability.
- Collaborate with US-based clients and stakeholders during IST night hours when required.
Required Skills :
- 3+ years of relevant software development experience.
- Strong proficiency in Python and FastAPI.
- Hands-on experience with AI / LLMs and production-level AI product development.
- Practical experience building AI agents, RAG pipelines and tool / function-calling workflows.
- Good knowledge of PostgreSQL and Redis.
- Experience with Docker, GCP / Cloud Run and CI/CD pipelines.
- Basic working knowledge of React.js or Next.js.
- Understanding of REST APIs, application architecture, deployment and production debugging.
- Excellent problem-solving and communication skills.
Preferred Qualifications :
- Experience deploying and maintaining AI applications in production.
- Familiarity with LLM orchestration frameworks and vector databases.
- Experience with cloud-native application development and monitoring.
Important Requirements :
- Must have demonstrable, hands-on experience delivering production-grade AI products.
- Must be comfortable working remotely and coordinating with US clients during IST night hours.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
ou will work closely with AI engineers, product teams, and domain experts to build intelligent document processing and knowledge automation solutions. Responsibilities include:
- Develop AI-powered document ingestion and processing pipelines.
- Build knowledge extraction engines using NLP, Machine Learning, and Generative AI.
- Develop document-to-knowledge compilers that transform PDFs, Word documents, policies, regulations, and manuals into structured knowledge.
- Build AI agents and Agentic AI workflows for enterprise automation.
- Develop rule extraction and rule generation frameworks from business documents.
- Create semantic search and enterprise knowledge retrieval solutions.
- Develop backend APIs and AI services using Python.
- Design and optimize document processing pipelines for scalability and performance.
- Build and maintain MySQL databases for knowledge repositories and AI applications.
- Integrate LLMs from providers such as OpenAI, Azure OpenAI, Gemini, Claude, and open-source ecosystems.
- Collaborate with cross-functional teams to design scalable AI architectures.
- Participate in code reviews and follow software engineering best practices.
- Continuously evaluate and adopt emerging AI and GenAI technologies.
REQUIRED SKILLS — PROGRAMMING & DEVELOPMENT
- Strong proficiency in Python and a solid understanding of Object-Oriented Programming (OOP).
- Experience building REST APIs and backend services.
- Experience working with JSON, XML, and structured data formats.
- Knowledge of software design patterns and scalable architecture.
- Strong debugging, analytical, and problem-solving skills.
ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
- Strong understanding of Machine Learning concepts and algorithms.
- Experience with Natural Language Processing (NLP) and Generative AI solutions.
- Hands-on experience with Large Language Models (LLMs).
- Understanding of prompt engineering techniques.
- Knowledge of Agentic AI concepts and AI agent architectures.
- Experience developing AI-powered applications and workflows.
TECHNOLOGY STACK
AI & GenAI: Python · OpenAI · Azure OpenAI · Hugging Face · Agentic AI Frameworks · LLMs · NLP · Machine Learning
Knowledge Systems: ChromaDB · Pinecone · FAISS · Vector Databases · Semantic Search
Document Processing: Docling · OCR · PDF Processing · Apache Tika · Document Intelligence
Backend: Python · FastAPI · Flask · REST APIs
Database: MySQL
Tools & Technologies: Git · Docker · JSON · CI/CD · Azure / AWS / GCP
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
- We are seeking a high-velocity Senior Technical Lead with an overall experience
- of 12+ years in software engineering who thrives in an environment of autonomy
- and rapid iteration. At Nomiso, we don't just write code; we build resilient systems.
- This role is designed for a builder who embraces our core philosophy: Build, Ship,
- Measure, Improve. You will be responsible for taking features from a raw concept
- to a live environment, ensuring that every deployment delivers high technical
- excellence and system stability. You are not just an executor; you are a technical
- owner and system architect who understands that the "Ship" is only the midpoint of the system lifecycle.
What We’re Looking For (Who You Are)
● AI Systems Architect (5+ years in AI - LLM, RAG, Context Engineering, React, Prompt): You've shipped multiple production LLM systems at scale. Deep understanding of RAG, fine-tuning, prompt optimization, inference scaling, and cost management. You make pragmatic trade-offs between
accuracy, latency, and cost.You are accountable for the high quality solution and timely shipment of the feature as per committed timeline.
● Technical Lead Manager (TLM): In this role you will do 70% technical work and 30% people management & project management work. You've led engineering teams (4-8+ engineers). You grow engineers through mentoring, clear feedback, and ownership. You balance shipping speed with technical excellence and team development.
● The "Builder" Mentality: You have a bias toward action. You prefer a
working feature over a perfect specification and understand the value of
getting software into the hands of users early. You will not leave the tech
debt for a long time. Tech debt will be continuously addressed as product matures.
● Pragmatic Architect: You choose the right tool for the job, balancing
long-term scalability with the immediate need for speed and delivery.
● Cross-functional engagement: Partner with Product, QA, and Solution
Architects, Project manager to align execution with outcomes
● Continuous Learner: You view "Improvement" as a mandatory phase, not an optional one. You are eager to refactor and pivot based on objective evidence.
Requirement
AI Expertise
- LLM APIs (OpenAI, Anthropic, Hugging Face), model selection and trade-offs. RAG pipeline architecture, fine-tuning strategies, prompt engineering, Agentic patterns, multi-step reasoning, reliability under uncertainty
Fullstack depth
● Backend: Python (FastAPI,
Django) and Node.js (Express,
Nest.js)
● Frontend: React (TypeScript,
state management, performance
optimization)
● Databases: PostgreSQL (query
optimization, schema design,
scaling)
● Infrastructure: AWS (Lambda,
ECS, RDS, S3), Docker, CI/CD,
monitoring
Leadership
● Managed engineering teams
(4-8+ engineers)
Category Requirement
● Experience mentoring and
growing engineers
● Track record of building
high-performing teams
● Comfortable with ambiguity and
rapid decision-making
Experience 12+ years in a technical-focused
engineering environment.
Education Degree in CS or equivalent professional
experience.
You will operate within a cross-functional squad, collaborating daily with Solution
Architects and other engineering peers. You will ensure that features are released
safely and frequently, and own the success of the product, by analysing the
insights and user feedback. Our hierarchy is flat; you are expected to provide
technical leadership and mentorship to junior peers while having a direct line of
communication with leadership regarding technical strategy and technical debt.
Applications on this job are not being reviewed actively. You may apply but please follow up with the company via other channels too.
Job Summary
We are looking for an experienced Python Developer with strong expertise in Generative AI (GenAI), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). The ideal candidate should have hands-on experience building and deploying AI-powered applications using Python, LangChain/LangGraph, and FastAPI.
Key Responsibilities
- Design, develop, and maintain scalable backend applications using Python.
- Build and implement Generative AI solutions using LLMs.
- Develop and optimize RAG-based applications and pipelines.
- Work with LangChain and LangGraph to build LLM-powered workflows and AI agents.
- Develop RESTful APIs and backend services using FastAPI.
- Integrate LLMs with enterprise applications, databases, and external services.
- Implement prompt engineering, context management, and response optimization.
- Work on vector databases and embedding models for semantic search.
- Ensure application scalability, performance, security, and reliability.
- Collaborate with cross-functional teams to deliver AI-driven solutions.
Mandatory Skills
- Strong hands-on experience in Python development.
- Practical experience with Generative AI and LLMs.
- Strong understanding and implementation experience of RAG architecture.
- Hands-on experience with LangChain and/or LangGraph.
- Experience developing REST APIs using FastAPI.
- Good understanding of LLM integration and prompt engineering.
Good to Have Skills
- Experience with OpenAI, Azure OpenAI, or other LLM providers.
- Knowledge of vector databases such as Pinecone, FAISS, Chroma, or Weaviate.
- Experience with embeddings and semantic search.
- Knowledge of Docker, Kubernetes, and cloud platforms (AWS/Azure).
- Exposure to AI agents and multi-agent systems.
- Experience with CI/CD and production deployment of AI applications.














