- Develop and implement LLM-based applications using OpenAI, Azure OpenAI, Claude, Gemini, or Llama models.

- Build RAG (Retrieval Augmented Generation) pipelines using vector databases (Pinecone, FAISS, Chroma, Weaviate, etc.).

- Design, test, and optimize prompts, system instructions, and agent workflows.

- Perform fine-tuning / supervised training of LLMs where required.

- Integrate LLMs with applications using Python, REST APIs, LangChain, LlamaIndex, etc.

- Work on NLP tasks such as text classification, summarization, and Q&A systems.

- Collaborate with engineering teams for deployment on AWS/Azure/GCP.

- Ensure model evaluation, performance tuning, and responsible AI compliance.

Required Skills :

- Strong knowledge of Generative AI, LLMs, Prompt Engineering

- Experience with :

a. LangChain / LlamaIndex / HuggingFace

b. RAG architecture and vector databases

c. Python, FastAPI/Flask

d. Embeddings, tokenization, model evaluation

- Experience deploying solutions on AWS / Azure / GCP

- Good understanding of NLP and ML fundamentals

Good to Have :

- Experience with Agentic AI / Multi-agent systems

- Knowledge of MLOps, LLMOps pipelines