AI/ML Engineer (GenAI / LangChain / RAG)
Location: Pune
Experience: 1–3 Years
Job Type: Full-Time
Work Mode: Onsite / Hybrid
About the Role:
We are hiring an AI/ML Engineer with hands-on experience in building AI-powered applications using Python and modern GenAI frameworks. The role involves working on LangChain workflows, RAG pipelines, vector databases, backend APIs, and LLM integrations.
Key Responsibilities:
- Develop AI-powered applications using Python and FastAPI
- Build and maintain LangChain / LangGraph workflows
- Implement RAG (Retrieval-Augmented Generation) pipelines
- Work with Vector Databases and embeddings
- Develop REST APIs and backend orchestration services
- Integrate LLM workflows into enterprise applications
- Debug and optimize AI application performance
- Collaborate with engineering teams on scalable AI solutions
Required Skills:
- Strong Python programming skills
- Experience with FastAPI / REST APIs
- Hands-on experience with LangChain and/or LangGraph
- Understanding of LLM workflows and prompt engineering
- Experience with Vector Databases and embeddings
- Basic understanding of RAG architecture
- Git/version control knowledge
- Strong debugging and problem-solving skills
Good to Have:
- Docker / Containerization
- AWS / Azure / GCP exposure
- AI Agent workflow understanding
- ML fundamentals
- Enterprise AI integration experience
Who Should Apply:
- Engineers with practical AI project experience
- Python backend developers transitioning into AI engineering
- Developers working on GenAI, RAG, or LLM-powered systems
- Candidates comfortable building production-oriented AI workflows
Who Should NOT Apply:
- Candidates with only theoretical AI knowledge
- Frontend-only developers
- Tutorial/demo-level LangChain exposure only
- Candidates without backend/API development experience
What We’re Looking For:
- Strong implementation capability
- Practical project ownership
- Fast learners with strong problem-solving mindset
- Team players comfortable in collaborative environments
Pay: From ₹1,000,000.00 per year
Benefits:
- Health insurance
- Paid time off
- Provident Fund
Application Question(s):
- Describe one AI/LLM project you have built using LangChain, LangGraph, RAG, or Vector Databases. Mention your exact role, technologies used, and deployment/implementation details.
- Which of the following technologies have you used in real projects?
(Python, FastAPI, LangChain, LangGraph, Vector DBs, RAG Pipelines, REST APIs, Docker, Cloud Platforms)
- Have you developed or deployed backend APIs for AI applications using FastAPI or similar frameworks?
- Explain how you handled embeddings, chunking, retrieval, or hallucination reduction in any AI application you worked on.
- hare your GitHub, portfolio, or any live/demo links related to AI/ML, GenAI, or backend development projects.
Education:
Experience:
- Python, langchain, RESTAPI: 1 year (Required)
Location:
- Pune, Maharashtra (Required)
Work Location: In person
