We are seeking a hands-on AI Tech Lead to design and build enterprise-grade LLM and RAG-based solutions. The role requires strong expertise in Generative AI, system design, and scalable architecture, along with the ability to lead development and optimize real-world AI applications.

Key Responsibilities

• Design and implement LLM-powered applications using RAG, embeddings, and agentic AI
• Build scalable end-to-end AI architectures integrating enterprise data
• Optimize LLM performance (RPM, TPM, latency, cost)
• Improve accuracy by handling hallucinations and retrieval issues
• Work with Azure AI Services and AI Gateways
• Ensure data security and masking for sensitive information
• Lead hands-on development (Python /APIs)

Core Skills

• Strong experience in Generative AI, LLMs, and RAG
• Expertise in:
• Prompt engineering (temperature, top-p)
• Vector databases & embeddings
• API integrations (OpenAI / Azure OpenAI)
• Solid coding in Python (mandatory), Java/Spring Boot (preferred)
• Experience in system design and scalable architectures

Must Have

• End-to-end LLM + RAG implementation experience
• Strong problem-solving & debugging skills
• Ability to translate business requirements into technical solutions
• Prior client-facing / leadership experience
• Good to Have
• Experience with MCP, Agentic AI
• Exposure to Banking / Financial domain

Ideal Candidate:

• A hands-on AI lead who can architect, code, hands on experience in production environment and scale real-world GenAI solutions in enterprise environments.

Are you looking for more jobs nearby? Find your favorite jobs now by visiting our online jobs page.