Key Responsibilities :

- Design and develop LLM-based applications using OpenAI and Microsoft Azure OpenAI.

- Build and optimize Retrieval-Augmented Generation (RAG) pipelines.

- Develop enterprise-grade GenAI solutions using LangChain and LlamaIndex.

- Implement knowledge retrieval systems using vector databases such as FAISS and Pinecone.

- Develop effective prompt engineering and LLM evaluation strategies.

- Collaborate with Data Engineers, Product Managers, and Engineering teams to deliver scalable AI solutions.

- Deploy, monitor, and optimize AI applications on Microsoft Azure.

- Improve model accuracy, performance, scalability, and response quality.

- Implement techniques to reduce hallucinations and improve grounding and reliability.

- Apply responsible AI practices, including PII protection, data security, and AI safety.

- Conduct experimentation and evaluation to continuously improve GenAI applications.

- Build production-ready AI solutions aligned with business requirements.

Required Skills :

- Strong hands-on experience with Python.

- Experience with Generative AI, LLMs, and NLP.

- Strong experience building RAG pipelines.

- Hands-on experience with OpenAI / Azure OpenAI.

- Experience with LangChain and/or LlamaIndex.

- Experience with vector databases such as FAISS, Pinecone, or equivalent.

- Strong knowledge of prompt engineering and LLM evaluation.

- Experience deploying AI solutions on Microsoft Azure.

- Understanding of model performance optimization and evaluation techniques.

- Knowledge of hallucination mitigation, PII protection, and responsible AI.

- Strong analytical and problem-solving skills.