Senior Associate Gen AI Engineer

Job Title: Senior Associate Gen AI Engineer
Experience: 3+ years
Job Type: Full Time
Location: Bavdhan, PUNE, work from office
Link - https://talenthire360.com/jobs/692d7dc1e0454f2aa0cf2c83
About Us
We are a dynamic technology services company delivering cutting-edge digital solutions to diverse global clientele. From real estate to healthcare, we tackle complex business challenges by integrating the latest technologies. Our team is currently expanding its AI capabilities, focusing on building intelligent agents, RAG pipelines, and scalable backend systems that solve real-world problems.
The Role
We are looking for a Senior GenAI Engineer with strong backend roots to join our engineering team. In this role, you will not just "wrap APIs"—you will architect and build complex AI Agents and Retrieval-Augmented Generation (RAG) systems that interact with varied data sources.
As a services company, we work on a wide array of projects. If you love Python, live in FastAPI, and have been experimenting with LangChain and LangGraph to build autonomous systems, this role is for you.
Key Responsibilities
Backend Development: Design and develop high-performance, asynchronous RESTful APIs using Python and FastAPI.
GenAI Engineering: Build and deploy production-grade RAG pipelines and AI Agents. You will be responsible for prompt engineering, context management, and reducing hallucinations.
Agentic Workflows: Use LangGraph to design stateful, multi-step agent workflows that can reason, plan, and execute tasks (not just chat).
Integration: Integrate LLMs (OpenAI, Anthropic, Llama 3, etc.) with external tools, databases, and third-party APIs.
Data & Embeddings: Manage Vector Databases (Qdrant, Pinecone, Weaviate, or pgvector) and optimize retrieval strategies for accuracy.
Deployment: Dockerize applications and assist in deploying AI microservices on cloud platforms (AWS/Azure/GCP).
Client Collaboration: Since we are a services company, you will occasionally interact with clients to understand their requirements and demo the cool AI solutions you’ve built.
Fine-Tuning & Model Adaptation: Execute Supervised Fine-Tuning (SFT) on open-source models (Llama 3, Mistral, Qwen) using LoRA and Q-LoRA adapters.
Must-Have Skills
Experience: 3+ years of professional software engineering experience.
Core Language: Expert proficiency in Python. You know your way around asyncio, Pydantic, and type hinting.
Backend Frameworks: Strong experience with FastAPI (preferred) or Flask/Django.
Generative AI Stack:
Hands-on experience with LangChain framework.
Experience building agents using LangGraph (managing state, cycles, and human-in-the-loop workflows).
Deep understanding of RAG (Retrieval Augmented Generation), including chunking strategies and embedding models.
Databases: Experience with SQL (PostgreSQL) and at least one Vector Database (Qdrant, Pinecone, Milvus, ChromaDB, etc.).
Version Control: Proficient with Git.
Nice-to-Have
Experience in a client-facing role or consultancy environment.
Basic familiarity with frontend tech (React/Next.js).
Cloud certifications (AWS/Azure).
Domain Knowledge: Background in Mechanical Engineering or Architecture.
Specialized Tools: Experience with CAD tools or 3D geometry libraries (reading/manipulating DXF/STEP files via Python).

Work arrangement
No