Role: Generative AI Engineer- wipro(immediate Joiners 1 month Notice Period)
Key Responsibilities
- Design and implement end-to-end RAG pipelines including ingestion, chunking, embeddings, and retrieval
- Develop and optimize LLM-based applications using Python
- Implement prompt engineering techniques to improve response quality and reduce hallucinations
- Work with vector databases (FAISS/Chroma) for semantic search and retrieval
- Build scalable APIs using FastAPI/Flask
- Deploy AI solutions using Docker, Kubernetes, and cloud platforms (AWS/Azure/GCP)
- Optimize retrieval performance, latency, and system scalability
- Debug and improve LLM and RAG pipeline performance
Required Skills
- Strong expertise in Python programming
- Hands-on experience with RAG architectures
- Experience working with LLMs and prompt engineering
- Knowledge of embeddings, tokenization, and retrieval systems
- Familiarity with LangChain / LlamaIndex / LangGraph
- Experience deploying AI systems into production
Preferred Skills
- Experience with vector databases (FAISS, Chroma)
- Knowledge of cloud platforms (AWS, Azure, GCP)
- Understanding of LLM evaluation and optimization techniques
This job is provided by Shine.com
