Generative AI Architect

Job Title: Generative AI Architect (Python, RAG, LLMs)

Job Summary

We are looking for a hands-on Generative AI Architect with strong expertise in Python, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) pipelines. The ideal candidate will design, build, and deploy end-to-end AI solutions using modern LLM frameworks and vector databases.

Key Responsibilities

• Design and implement end-to-end Generative AI solutions
• Build and optimize RAG pipelines using Python
• Work with LLMs for prompting, tuning, and evaluation
• Develop and manage vector databases (FAISS / Chroma)
• Implement prompt engineering and guardrails for responsible AI
• Integrate LLMs with APIs and backend systems
• Deploy AI pipelines into production environments
• Monitor performance, optimize latency, and improve retrieval accuracy
• Ensure security, domain guardrails, and responsible AI practices

Required Skills & Experience

• 4+ years of hands-on Python development
• 4+ years of experience in Generative AI
• 1+ year of LLM tuning experience
• Experience designing at least 2 end-to-end AI implementations
• Strong understanding of RAG architecture and optimization
• Experience with vector databases (FAISS / Chroma)
• Familiarity with orchestration frameworks such as LangChain, LangGraph, or LlamaIndex
• Understanding of embeddings, tokenization, and retrieval systems
• Experience deploying models or AI pipelines to production
• Knowledge of Responsible AI and security best practices

Good to Have

• Experience with Docker
• Exposure to basic MLOps practices
• Cloud fundamentals (Azure / AWS / GCP)
• API development and integration experience

Interested candidates send your cv to monisha.m@liveconnections.in or whats app 9940315611