Source description
About the role
Key Responsibilities : - Design, develop, and deploy AI/ML applications using Python.- Build LLM-powered applications using OpenAI, Llama, Gemini, Claude, or similar models.- Develop scalable RAG pipelines for enterprise search and document intelligence.- Build Agentic AI workflows using LangChain and LangGraph.- Implement Prompt Engineering and semantic search using Vector Databases.- Deploy AI applications on AWS/Azure using Docker and Kubernetes.- Develop REST APIs using FastAPI or Flask.- Collaborate with global clients and deliver production-ready AI solutions.- Ensure scalability, monitoring, security, and compliance.Required Skills : - 68 years of experience in AI/ML, Data Science, or Software Engineering.- Strong Python programming skills.- Hands-on experience with LLMs and Generative AI.- Experience with RAG, LangChain and/or LangGraph.- Experience building Agentic AI solutions.- Prompt Engineering expertise.- Experience with Vector Databases (Pinecone, FAISS, ChromaDB, Qdrant, Azure AI Search).- Experience deploying AI applications on AWS and/or Azure.- FastAPI/Flask, Docker, Kubernetes, and REST APIs.- Strong understanding of embeddings and enterprise AI architecture.Preferred Qualifications : - Bachelor's or Master's degree in Computer Science, AI, Data Science, or related field.- Experience with LoRA/PEFT fine-tuning.- Exposure to LangSmith, Langfuse, MLflow, or Arize.- Experience with MLOps and CI/CD.- Experience working with US/EU clients.- Exposure to OCR or Document Intelligence is a plus. (ref:hirist.tech) .
More at Innomatics Research Labs