Core Responsibilities

• Architect and deploy LLM-based solutions at scale (e.g., enterprise chat agents, document intelligence, domain-specific RAG)
• Design agentic workflows using LangChain, A2A protocols, or custom-built orchestration layers
• Develop and optimize prompt chaining logic, vector search strategies, and context management approaches (e.g., with MCP)
• Integrate solutions with cloud-native platforms (Databricks, Azure Foundry), APIs, and enterprise data ecosystems
• Lead technical design reviews, enforce best practices in code structure, testing, and observability
• Conduct performance evaluations, token cost optimizations, and maintain reusability across solutions
• Mentor Associate and AI Engineers through pair programming, design guidance, and code reviews
• Stay ahead of emerging GenAI tooling and make recommendations for adoption in our stack

Required Skills

• 4–6+ years of experience in AI/ML engineering, with minimum 2 years working on GenAI/LLM use cases
• Deep proficiency in Python,



with fluency in libraries like OpenAI, Pydantic, Transformers, LangChain, FAISS, and Pandas
• Demonstrated experience in building and deploying LLM-integrated applications using OpenAI or similar APIs
• Solid knowledge of vector databases, prompt engineering strategies, and LLM context optimization
• Hands-on with Azure cloud stack, GitHub/Azure DevOps CI/CD, and microservice/API design

Preferred Skills

• Experience with MCP (Model Context Protocol) and A2A orchestration in a production environment
• Working knowledge of LLM evaluation techniques (latency, relevance, hallucination mitigation)
• Open-source GenAI project contributions or demonstrable GitHub repositories
• Exposure to Databricks, Azure Foundry, and integration with enterprise-scale platforms
• Familiarity with prompt safety, guardrails, and observability frameworks like Trace loop, Prompt layer, etc.

📌 Senior AI Engineer (Bengaluru)
🏢 Ecolab
📍 Bengaluru