Are you excited about building real-world GenAI applications using LLMs, RAG pipelines, and agentic workflows? Were looking for a hands-on Python / GenAI Engineer who can build scalable, production-grade AI systems.

What Youll Do :

- Develop production-grade Python applications for GenAI use cases

- Build and optimize RAG pipelines (embedding, retrieval, context injection)

- Implement LangChain / LlamaIndex-based orchestration workflows

- Integrate and consume Azure OpenAI services

- Design and develop REST APIs for AI applications

- Work with vector databases (Pinecone, Azure AI Search, Qdrant)

- Manage session/context using Redis in agentic workflows

- Implement NL-to-SQL pipelines for structured data querying

Must-Have Skills :

- 5+ years of experience in Python (production-level)

- Hands-on with LangChain or LlamaIndex

- Experience with Azure OpenAI integration

- Strong in REST API development

- Experience with Redis (context/session management)

- Hands-on with Vector DBs (Pinecone / Azure AI Search / Qdrant)

- Experience building RAG-based systems

- Knowledge of NL-to-SQL implementation in production

Good to Have :

- Experience in feedback loops/self-learning pipelines

- Model performance optimization & continuous improvement

Work Details :

Timing : 11 :00 AM 8 :00 PM (with ~4 hours overlap with US EST if required)

Location : Hybrid (Pune, Bangalore, Mumbai, Hyderabad, Noida) and Remote all locations

Contract : 6 Months (C2H extendable based on performance)

If youre passionate about GenAI, LLMs, and building scalable AI products, this is your chance!

The job is for:

Women candidates preferred

May work from home

For women joining back the workforce