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)

Your Opportunity

• Own and drive business features into tech requirements
• Design & develop large scale real time server side systems
• Quickly create quality prototypes
• Staying updated on emerging technologies
• Ensuring that all deliverables adhere to our world class standards
• Promote coding best practices
• Mentor and develop junior developers in the team

Required Experience:

• 4+ years of relevant experience as described below
• Excellent grasp of Core Java, Multi Threading and OO design patterns
• Experience with Scala, functional, reactive programming and Akka/Play is a plus
• Excellent understanding of data structures and algorithms
• Solid grasp of large scale distributed real time systems
• Prior experience on building a scalable and resilient micro service
• Solid understanding of relational databases, NoSQL databases and Caching systems
• Good understanding of Big Data technologies such as Spark, Hadoop is a plus
• Experience on one of AWS, Azure or GCP

Who you are :

• You have excellent and effective communication and collaborative skills
• You love problem solving
• You stay up to date with the latest technologies and then apply them in real life
• You love paying attention to detail
• You thrive in meeting tight deadlines and prioritising workloads
• Ability to collaborate across multiple functions

Education:

Bachelor’s degree in Engineering or equivalent experience within the field

We're looking for exprienced Python developers with over 2+ years of production experience and strong expertise in building web applications and APIs using Python, Django and DRF. We are looking for cadidates who are go-getters and are leaning towards leadership positions. Candidates must have a proven history of building, scaling, optimising and securing Python based backends and APIs using a microservice architecture.

Bonus Skills : Experience with ReactJs, Node.js, FastAPI

We would prefer candidates who can join immediately or are currently serving their notice period. Jumpers please excuse, your application will be ignored

Key Skills Required

1. Proficiency in Python 3.x based web and backend development
2. Solid understanding of Python concepts
3. Strong experience in building web applications using Django
4. Experience building REST APIs using DRF or Flask
5. Experience with some form of Machine Learning (ML)
6. Experience in using libraries such as Numpy and Pandas
7. Hands on experience with RDBMS such as Postgres or MySQL including querying
8. Comfort with Git repositories, branching and deployment using Git
9. Working experience with Docker
10. Basic working knowledge of ReactJs
11. Experience in deploying Django applications to AWS,Digital Ocean or Heroku

Responsibilities

1. Understanding requirement and congributing to engineering solutions at a conceptual stage to provide the best possible solution to the task/challenge
2. Building high quality code using coding standards based on the SRS/Documentation
3. Building component based, maintainable, scalable and reusable backend libraries/modules.
4. Building & documenting scalable APIs on the Open Spec standard
5. Unit testing development modules and APIs
6. Conducting code reviews to ensure that the highest quality standard are maintained
7. Securing backend applications and APIs using industry best practices
8. Troubleshooting issues and fixing bugs raised by the QA team efficiently.
9. Optimizing code
10. Building and deploying the applications

• Employment type

  Full-time

• Lead a full product development lifecycle from ideation, design, development, to roll out and support
• Own the delivery of multiple features of the product end to end while hands-on in development as well
• Advocate best development practices such as continuous integration/continuous delivery, automation (testing and infrastructure)

1. 7+ Years’ of experience, managing teams of 5+ people
2. Must have excellent programming, debugging and scripting skills with a solid understanding of Object Oriented Design principles.
3. Proficiency in at least two of the following: Java, NodeJS, Go, JavaScript, Python programming stacks, and passion for software engineering and craftsman-like coding prowess
4. Knowledge of software practices like refactoring, clean code, domain driven design, Encapsulation etc
5. Hands on experience managing databases like MongoDB, Cassandra, Redis.
6. Exposure to event driven systems and event streaming engines like Kafka
7. Good knowledge of DevOps tooling like docker, kubernetes, ansible/chef, AWS.