Python Developer

Experience: 5+ years production software engineering, with 2+ years working directly on LLM or agent systems in production. 

Location: Remote 

To streamline and fast-track screening, please submit your details here (if you haven’t already): https://airtable.com/appbtkr4odapnb5I6/pagqo91lKv3VJg3GT/form 

We’ll review your responses as part of the initial screening process. Please make sure you complete and submit all details through the form to be considered for the next stage. Submissions outside the form may not be considered.

Why This Role Matters

Terrabase builds agent infrastructure that enterprise customers rely on daily for SQL generation, forecasting, data analysis, and artifact delivery. Our orchestration layer routes between specialized sub-agents, manages typed handoff contracts, runs structured eval suites, and enforces correctness across every turn.

This is not a research-prototype role. You will build and evolve agent architecture, but always in service of making the system observable, typed, evaluated, recoverable, and boringly reliable in production.

What You Will Do

Own the harness architecture and middleware stack. Our LangGraph orchestrator routes between sub-agents through a layered middleware stack: file upload handling, source resolution, local context, workspace sync, state hydration, aggregation barriers, and typed handoff contracts. You will extend this stack, enforce its contracts in code, and keep it operational as routing logic and agent surfaces evolve.

Maintain typed contracts and boundaries. Agent handoffs at Terrabase carry typed contracts with barrier conditions and retry predicates. You will design these contracts, enforce them with strict typing, manage backward compatibility when contracts change, and write the contract tests that prevent silent regressions.

Own the eval suites. We run structured eval suites across routing decisions, context-resolution accuracy, multi-turn coherence, visual reference alignment, and artifact correctness. You will extend coverage, write new evals where gaps exist, and build CI gates that block releases when regressions are detected. A routing change or prompt change with no eval coverage does not ship.

Triage production failures and close the loop. When an agent turn fails in production, you will trace it in LangSmith, identify the failure class, and convert it into a durable regression test. You will own the release gates, keep prompts and runtime contracts in sync, manage feature flag rollout risk, and remove dead paths as the system evolves.

Own SQL and artifact correctness. Our agents generate SQL over customer schemas and produce structured artifacts (reports, dashboards, data sheets) under a strict schema contract. You will own the correctness layer: source grounding, schema-aware validation, provenance surfaces, and the eval infrastructure that catches generated artifact failures before they reach customers.

Build and maintain HITL workflows. Human-in-the-loop checkpoints let users intervene, redirect, or approve mid-chain. You will design these workflows, enforce their resumable state contracts, and ensure they degrade gracefully when interrupted.

Instrument for traceability. You will extend LangSmith tracing coverage, add structured span annotations, and build the tooling that lets us diagnose a bad agent turn from production trace data alone, without requiring a local reproduction.

What We Are Looking For

• 5+ years production software engineering, with strong Python fundamentals
• 2+ years working hands-on with LLM-based systems: agent loops, tool use, context management, or inference pipelines
• Experience with LangGraph, LangChain, OpenAI/Anthropic tool-use systems, or equivalent multi-step agent/runtime orchestration
• Practical eval engineering: you have built or extended eval harnesses, written automated test cases for agent behavior, and treated evaluation as an ongoing engineering discipline
• Strong engineering hygiene: strict typing, small interfaces, contract tests, clear schema migrations, and CI discipline
• Ability to debug from production traces and artifacts, not only local reproductions
• Comfort working across prompts, Python runtime code, TypeScript product surfaces, data systems, and eval infrastructure
• Systems thinking: you design for observability, recovery, and state management, not just the happy path
• Maintenance ownership mindset: you triage, close loops, and leave systems more debuggable than you found them
• Pragmatic judgment: you can distinguish between reliability-critical infrastructure and speculative abstraction

Bonus Points

• HITL workflow design: checkpoints, approvals, mid-chain interrupts, resumable state
• Context engineering depth: chunking strategies, retrieval-augmented generation, semantic routing, re-ranking
• Experience with LangSmith, Weights and Biases, or similar trace and evaluation platforms
• Prior work shipping agent systems to enterprise customers where SQL or data correctness is a hard requirement
• Experience with mypy, Pydantic contracts, or strict typing disciplines in a production Python codebase

Life at Terrabase

We are a sharp, focused, fully remote team building agent infrastructure that enterprise customers trust with their data. You will work directly alongside the engineer who designed this harness, with broad ownership, generous compute budgets, and a culture that treats reliability as a product requirement, not a research topic.

Terrabase is an equal-opportunity employer. We celebrate diversity and are committed to building an inclusive environment for every team member.

Role Overview

We are seeking a Junior Developer with 1-3 year’s experience with strong foundations in Python, databases, and AI technologies. The ideal candidate will support the development of AI-powered solutions, focusing on LLM integration, prompt engineering, and database-driven workflows. This is a hands-on role with opportunities to learn and grow into advanced AI engineering responsibilities.

Key Responsibilities

• Develop, test, and maintain Python-based applications and APIs.
• Design and optimize prompts for Large Language Models (LLMs) to improve accuracy and performance.
• Work with JSON-based data structures for request/response handling.
• Integrate and manage PostgreSQL (pgSQL) databases, including writing queries and handling data pipelines.
• Collaborate with the product and AI teams to implement new features.
• Debug, troubleshoot, and optimize performance of applications and workflows.
• Stay updated on advancements in LLMs, AI frameworks, and generative AI tools.

Required Skills & Qualifications

• Strong knowledge of Python (scripting, APIs, data handling).
• Basic understanding of Large Language Models (LLMs) and prompt engineering techniques.
• Experience with JSON data parsing and transformations.
• Familiarity with PostgreSQL or other relational databases.
• Ability to write clean, maintainable, and well-documented code.
• Strong problem-solving skills and eagerness to learn.
• Bachelor’s degree in Computer Science, Engineering, or related field (or equivalent practical experience).

Nice-to-Have (Preferred)

• Exposure to AI/ML frameworks (e.g., LangChain, Hugging Face, OpenAI APIs).
• Experience working in startups or fast-paced environments.
• Familiarity with version control (Git/GitHub) and cloud platforms (AWS, GCP, or Azure).

What We Offer

• Opportunity to work on cutting-edge AI applications in permitting & compliance.
• Collaborative, growth-focused, and innovation-driven work culture.
• Mentorship and learning opportunities in AI/LLM development.
• Competitive compensation with performance-based growth.

Strong Full stack/Backend engineer profile

Mandatory (Experience): Must have 2+ years of hands-on experience as a full stack developer (backend-heavy)

Mandatory (Backend Skills): Must have 1.5+ strong experience in Python, building REST APIs, and microservices-based architectures

Mandatory (Frontend Skills): Must have hands-on experience with modern frontend frameworks (React or Vue) and JavaScript, HTML, and CSS

Mandatory (Database Skills): Must have solid experience working with relational and NoSQL databases such as MySQL, MongoDB, and Redis

Mandatory (Cloud & Infra): Must have hands-on experience with AWS services including EC2, ELB, AutoScaling, S3, RDS, CloudFront, and SNS

Mandatory (DevOps & Infra): Must have working experience with Linux environments, Apache, CI/CD pipelines, and application monitoring

Mandatory (CS Fundamentals): Must have strong fundamentals in Data Structures, Algorithms, OS concepts, and system design

Mandatory (Company) : Product companies (B2B SaaS preferred)

Preferred

Preferred (Location) - Mumbai

Preferred (Skills) : Candidates with strong backend or full-stack experience in other languages/frameworks are welcome if fundamentals are strong

Preferred (Education) : B.Tech from Tier 1,Tier 2 institutes

Strong AI & Full-Stack Tech Lead

Mandatory (Experience 1): Must have 5+ years of experience in full-stack development, including Python for backend development and React/JavaScript for frontend, along with API/microservice integration.

Mandatory (Experience 2): Must have 2+ years of experience in leading technical teams, coordinating engineers, and acting as a system integrator across distributed teams.

Mandatory (Experience 3): Must have 1+ year of hands-on experience in AI projects, including LLMs, Transformers, LangChain, or OpenAI/Azure AI frameworks.

Mandatory (Tech Skills 1): Must have experience in designing and implementing AI workflows, including RAG pipelines, vector databases, and prompt orchestration.

Mandatory (Tech Skills 2): Must ensure backend and AI system scalability, reliability, observability, and security best practices.

Mandatory (Company): Must have experience working in B2B SaaS companies delivering AI, automation, or enterprise productivity solutions

Tech Skills (Familiarity): Should be familiar with integrating AI systems with enterprise platforms (SharePoint, Teams, Databricks, Azure) and enterprise SaaS environmentsx

Mandatory (Note): Both founders are based out of Australia, design (2) and developer (4) team in India. Indian shift timings.

We are seeking a motivated and detail-oriented Junior Backend Engineer to join our team. The role involves developing and maintaining backend systems using Django and Python, while also managing on-premises hardware and deployments. You will work closely with cross-functional teams to ensure our software is reliably configured, deployed, and maintained in an on-prem environment.

Key Responsibilities

Backend Development: Design, develop, and maintain backend services and APIs using Python (Django or Flask).

On-Prem Deployment: Install, configure, and manage software on on-premises hardware, including servers and networking equipment.

Database Management: Design database schemas, write efficient queries, and optimize data access layers (PostgreSQL, MySQL, etc.).

API Integration: Implement and maintain RESTful APIs and integrate with third-party services.

Troubleshooting & Debugging: Diagnose and resolve application and infrastructure issues to ensure high availability.

Version Control & CI/CD: Use Git for version control and contribute to continuous integration and delivery pipelines (GitHub Actions, Jenkins, etc.).

Security & Compliance: Work with the team to ensure software and infrastructure meet security and compliance requirements.

Documentation: Maintain clear, comprehensive documentation for your code, configurations, and on-prem deployment processes.

Requirement:

• Min 2-3 Year Experience. Preferably in the E-commerce domain. 
• Proficient with both MySQL and NoSql Databases (Elastic, Mongo)
• Strong hold on  Python
• Experience with JavaScript/JQuery
• Ability to do software design for a enterprise web application
• Working knowledge of a MVC front-end framework
• Proficient in HTTP protocol, REST APIs, JSON
• Ability to do database design and modeling
• Proficient in OOPS concepts and writing code using classes
• Ability to write modular and clean code

About KAFQA

At Kafqa, we are building the next generation performing arts platform. Our mission is to transform how India learns, performs & watches performing arts. Our launch services consist of technology-enabled dance classes in our proprietary studios, production facilities, and social media broadcasting & competitions.

Founder & Team

The founder is Shariq Plasticwala. He is a graduate of IIT Bombay & Stanford GSB. He was part of the founding team of Amazon India where he played a key role for over 8 years. Among his roles at Amazon, he was the CEO of Amazon’s first joint venture in India and a Board Member of Amazon’s payments business. The other members of the founding team consisted of senior executives from Shiamak Davar & Byju’s.

Background

•   At least 6+ years experience in back-end development in a fast-paced environment, working in Python & Django Framework
• Should Have experience leading a team.
•   Deep understanding of technologies used in web products, including Rest APIs
•   Sound understanding of SQL/NoSQL databases such as PostgreSQL and MongoDB.
•   Deep familiarity with UNIX, major cloud platforms (AWS, Azure), DevOps.
•   Understanding of databases, and related tools, paradigms.

Opportunity

Here are some of the things you might have to do on any given day:

•   Developing APIs and endpoints for deployments of our product.
•   Infrastructure Development such as building databases, creating and maintaining automated jobs.
•   Build out the back-end to deploy and scale our product.