Python Developer

AI Engineer

LLMs, Agents & AI Services

📍 Mumbai (On-site) | Full-time | 2-4 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

AI is core to how we design, deliver, and scale software for our customers.

We are hiring an AI Engineer for a dedicated client engagement building a complex production AI platform, working on the AI capabilities and agentic features at the core of the product.

The mandatory requirement for this role is at least one AI feature personally shipped to production for real users, with operational ownership.

The role suits someone who thinks quickly on solutioning, can take an ambiguous problem to a working prototype in days, and has the discipline to carry it through to production with predictable economics.

You will work alongside the Senior AI Engineer and the wider pod, with ownership of parts of the AI surface area of the product.

Responsibilities:

Solutioning and POCs

Translate ambiguous customer problems into working POCs at speed.

Pick the right model, framework, and architecture, and demonstrate value early before scaling investment.

LLM Application Development

Build AI features and services using LLM APIs from OpenAI, Anthropic, Google, and self-hosted open-weight models (Llama, Qwen, Mistral).

Choose the right model per use case based on cost, latency, capability, and context-window trade-offs.

Agentic System Design

Design and implement agentic workflows using LangGraph, CrewAI, AutoGen, LlamaIndex Agents, or custom orchestration.

Cover tool use, planning, memory, and multi-step reasoning appropriate to the problem.

API and Service Development

Build production AI services and APIs using Python and FastAPI.

Handle streaming responses, async processing, structured outputs, retries, and graceful degradation when models or tools fail.

Retrieval and Tool Integration

Implement RAG pipelines with vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma), embeddings, chunking strategies, hybrid search, and reranking.

Integrate external tools, internal APIs, and document sources through tool-calling and MCP-style patterns.

Cost Analysis and Unit Economics

Model the per-request and per-user cost of every AI feature before it ships.

Track token usage, prompt caching, batching, and model-routing strategies.

Drive measurable improvements in unit economics.

Production Hardening

Add observability and tracing (LangSmith, Langfuse, OpenTelemetry), guardrails, content safety checks, prompt injection defences, and fallback behaviour.

Prompt Engineering and Evaluation

Design, test, and iterate prompts with measured outcomes.

Build evaluation harnesses for accuracy, hallucination, latency, and cost.

Run benchmarks across models and prompt variants before locking in a design.

Requirements:

AI Feature Shipped to Production (Mandatory)

Must have personally built and shipped at least one AI feature that runs in production for real users, with operational ownership.

POCs, internal demos, and one-off scripts do not qualify.

2 to 4 Years of Professional Software or AI Engineering Experience

With at least one production AI feature owned end to end.

Strong Python Proficiency and API Development with FastAPI

Comfort with type hints, async, packaging, testing, streaming responses, and authentication.

Production-grade Python, not notebook-only code.

Hands-on Depth Across the LLM and Agent Stack

Working experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or self-hosted open-weight models (vLLM, Ollama, Together, Replicate).

Working familiarity with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Working knowledge of RAG, embeddings, and vector databases (Pinecone, Weaviate, Qdrant, pgvector, Chroma).

Solutioning Speed and POC Velocity

Demonstrated ability to move from a fuzzy problem to a working prototype in days.

Strong instinct for what to build first, what to defer, and what to throw away.

Cost Discipline for Production AI

Ability to calculate, monitor, and optimise the cost of LLM APIs, tokens, embeddings, vector store usage, and infrastructure.

Treats unit economics as a first-class concern.

AWS Familiarity

Working knowledge of EC2, S3, IAM, and at least one of Bedrock, SageMaker, or equivalent.

Comfortable in a Fast-Moving Environment

Self-directed, comfortable with ambiguity, takes ownership without being asked, and ships under shifting priorities.

Strong Written and Spoken English Communication

Able to explain trade-offs to non-AI engineers, designers, product managers, and clients in plain language.

Nice to Have

• fine-tuning or LoRA, QLoRA, PEFT exposure
• MCP server authoring
• eval framework experience (LangSmith, Promptfoo, Ragas, DeepEval)
• open-source AI contributions
• multi-modal models (vision, audio)

We are looking for a Python with the following experience and expertise:

• Proficiency in developing RESTful APIs using Flask, Django, or FastAPI.
• Hands-on experience with ORMs for database query mapping.
• Experience in designing, developing, and maintaining application integrations/connectors using REST APIs, SCIM, LDAP, webhooks, or similar integration technologies.
• Strong understanding of API authentication (OAuth 2.0, JWT, API Keys, Basic Auth) and integration best practices.
• Experience in writing unit test cases, ensuring code coverage, and API testing.
• Hands-on experience with Postman for API validation and testing.
• Minimum 2 years of experience working with any major cloud platform (AWS, Azure, or GCP).

Preferred:

• Experience building identity/IAM connectors or integrating enterprise applications with Identity Governance (IGA), IAM, HRMS, ERP, CRM, or SaaS platforms.

As a Tech Lead I (Backend) at Gocomet, you will be pivotal in driving backend development initiatives. Your role will involve leading the design and implementation of robust backend systems, ensuring high performance and responsiveness to requests from the front-end.

You will work closely with other team leads and departments to define and meet the technical and business requirements.

Roles and Responsibilities:

• Backend vision & ownership: Architect and implement scalable and efficient backend solutions, contributing significantly to the design and overall architecture, keeping in mind a long term vision of the product & scale.
• Optimize Performance: Focus on optimizing the application for maximum speed and scalability, including database optimization, effective caching strategies, improving code health, code design & refactoring, etc.
• Technical Innovation: Suggest innovative solutions wherever required for problems related to new product requirements & scale related issues. Stay abreast of emerging backend technologies and trends, advocating and leading the adoption of technologies that will give a competitive edge to our products.
• Mentor and Guide: Provide mentorship and guidance to backend development team members, ensuring the dissemination of best practices and efficient use of technology stacks. Take ownership of hiring & building a high quality backend team.
• Quality Assurance: Uphold high standards in code quality, including rigorous code review processes, and ensure adherence to industry best practices in backend development.

Experience & Skills:

• Backend Expertise: 4-6 years of experience in backend development, with a deep understanding of server-side logic, architecture design & handling scalability issues.
• Cloud & DevOps exposure: Experience with Cloud (GCP or AWS) with a deep understanding of different services, resources utilisations, CI/CD pipelines, Observability tools (Sentry, New Relic / Datadog, etc.) and an ability to debug infra related issues.
• Strong Technical Skills: Strong expertise in a Backend development framework (preferably Ruby on Rails but not mandatory), SQL & NoSQL database technologies.

(like Postgresql and MongoDB), Caching (Redis), Async job frameworks (like Sidekiq), etc.

• Problem-Solving Ability: Strong analytical and problem-solving skills, research ability with a proven track record of delivering high-quality software solutions.
• Leadership Skills: Demonstrated experience in mentoring backend development teams and taking complete tech ownership.
• Communication Skills: Excellent verbal and written communication skills, with the ability to clearly articulate technical challenges and solutions to both technical and non-technical team members.
• Continuous Learning: A commitment to continuous learning and staying current with the latest backend development trends and technologies.

Benefits:

• Collaborative and innovative work environment.
• Dynamic & high-performing team that thrives in a fast-paced environment.
• Opportunities for professional growth and development.
• Cutting-edge technology stack and tools.
• Make a significant impact on our products and the user experience.
• Join a team of passionate, creative, and driven individuals.
• 5 Days working.
• Flexible Working Hours.
• Experience good work culture with regular fun activities.
• Health medical insurance coverage with Family, etc.

Job Location: Bangalore

Why Gocomet?

GoComet is a dynamic SaaS start-up that provides AI-powered transportation visibility solutions to revolutionize the trillion-dollar logistics sector. At GoComet, we are revolutionizing the logistics sector one day at a time, and every team member is committed to making it a reality.

We're seeking individuals who embody our core values, character, and attitude. While we recognize that skills can be developed with the right mindset and learnability, we prioritize those who share our philosophy. Our recruitment processes reflect this belief.

Look no further if you're looking for a diverse, talented, and vibrant workplace that recognizes and rewards hard work. We're ambitious, fast-paced, and unafraid to experiment, fail, learn, and ultimately succeed. This is us! Join our team if you share our culture and values.

We're an equal-opportunity employer. We welcome qualified applicants from all races, colors, religions, sexes, nationalities, sexual orientations, gender identities, and abilities.

We are hiring for multiple positions.

For any queries, feel free to write to Know more about us:

https://www.youtube.com/watch?v=YxGt9ZCkaA8 https://youtu.be/jv9cAsgenSE https://www.youtube.com/watch?v=Er0dHqxaaXc https://youtu.be/0ql1eCVhiWA

Roles & Responsibilities:

• You will be coordinating our enterprise account-specific teams called squads, consisting of members from engineering, machine-learning, and conversation-design teams.
• There are five working groups in the organization, (i) Business (ii) Research (iii) Solutions (iv) Product, and (v) Operations, where you will be joining the Solutions, working group.
• You will be collaborating with the sales team to design an appropriate solution to the customer's problems and help them showcase the value of the product.
• You will be collaborating with the operations team to ensure we are not compromising on our quality standards.
• You will also be co-working with the product working group to help them improve the overall platform and to prioritize the high-impact initiatives in the roadmap.

Work you will be doing:

• You will be building bespoke voice bots for enterprise clients using internal tools.
• You're expected to help build the Solutions stack whose goal is to reduce the amount of effort put into building our voice bots. 
• You will be involved in analyzing client calls where you're expected to use either data pipelines or SQL to get insights into caller behavior.

• Professional experience of at least 1 year.
• Has experience with integrating or building HTTP APIs
• Has hands-on experience working with Python
• Good communicator

Optional Requirements:

• Has experience working in any of Django Rest Framework, Redis, Celery

Skit uses a microservices architecture where we employ both HTTP and GRPC to communicate between our services

We are actively seeking software development engineers who are interested in designing robust trading systems and refining programs to efficiently manage various types of financial market data that facilitate our quantitative investment research. By designing and improving the firm's internal applications, the SDE will play a key role in expanding the firm's trading capabilities.

Responsibilities:

• Management & scaling up existing infrastructure for high-frequency market data capture.
• Develop a scalable and consistent data handling infrastructure for the above data to facilitate efficient backtesting of quantitative investment strategies.
• Perform R& D; to build a software platform in Python for backtesting various kind of investment strategies using the above databases.
• This will involve studying the strategy development process and performance evaluation metrics.
• Develop autopilot risk-management systems to monitor live performance of the Portfolio.
• Improve the existing algorithms to achieve better execution price and reduce the latency.

Requirements:

Our ideal candidate would have graduated with a degree in computer science from a top university with 1-3 years industry experience, along with:

• High Level of proficiency in Python and good knowledge of Matlab/C++/C#.
• Past experience in dealing with large datasets and Knowledge of database administration and network programming will be a plus.
• Well-versed in software engineering principles, frameworks and technologies.
• The ability to manage multiple tasks in a fast-paced environment.
• Excellent analytical and problem solving abilities.
• A keen interest in learning about the financial markets.