Role : Gen AI Engineer

Exp : 2 to 3 Yrs

Location : Pune

Notice period : Immediate to 30 Days

Role Summary :

We are looking for an experienced GenAI Engineer to design, build, and deploy intelligent, autonomous AI systems. The role involves working on Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, and Agentic AI frameworks to solve real-world enterprise problems.

Key Responsibilities :

- Design, develop, and deploy Generative AI and Agentic AI solutions using LLMs

- Build and optimize RAG pipelines with vector databases (FAISS, Pinecone, Weaviate, etc.)

- Develop multi-agent systems using frameworks like LangChain, LangGraph, AutoGen, CrewAI

- Integrate LLMs with enterprise systems, APIs, tools, and workflows

- Fine-tune and prompt-engineer LLMs for domain-specific use cases

- Implement evaluation, monitoring, and guardrails for GenAI systems

- Collaborate with product, data, and cloud teams for scalable deployment

- Ensure performance, cost optimization, security, and compliance

Mandatory Skills :

- Python (Strong proficiency) : AI/ML fundamentals - NLP, Deep Learning, Transformers

- Generative AI : LLMs (OpenAI, Azure OpenAI, Gemini, Anthropic, LLaMA, etc.)

- Agentic AI frameworks : LangChain / LangGraph / AutoGen / CrewAI

- RAG architecture and vector databases

- Prompt engineering - LLM orchestration

- REST APIs, microservices integration

Good to Have :

- Fine-tuning LLMs (LoRA, PEFT)

- Experience with MLOps / LLMOps (MLflow, Kubeflow, monitoring tools)

- Cloud platforms : AWS / Azure / GCP