AI Developer

Overview

Design, build and scale AI-powered applications and full stack solutions across the enterprise, combining large language models, agentic workflows and cloud-native engineering.

What you'll do

• Design and build AI-powered applications using Large Language Models, agentic AI workflows, and Retrieval-Augmented Generation (RAG) solutions built on enterprise knowledge sources.
• Integrate AI services with business applications and external systems, and continuously evaluate, optimize, and monitor AI application performance and quality.
• Build responsive, modern frontend applications and scalable backend services and APIs, using reusable components and clean, maintainable code.
• Deploy and manage applications on cloud platforms (preferably AWS), building CI/CD pipelines, containerizing with Docker, and orchestrating workloads with Kubernetes.
• Design and manage SQL and NoSQL databases, integrate enterprise systems and third-party services, and ensure secure, compliant handling of data.
• Collaborate closely with product teams to translate business requirements into technical solutions, and implement monitoring, logging, and observability best practices.

What you'll need

• Strong understanding of LLMs, Prompt Engineering, RAG, and Agentic AI concepts, with hands-on experience using frameworks such as LangGraph, LangChain, or LlamaIndex.
• Experience integrating AI models through OpenAI, Anthropic, Bedrock, Azure OpenAI, or equivalent services, along with working knowledge of vector databases and semantic search.
• Strong proficiency in Python, with experience building APIs using FastAPI, Flask, or similar frameworks, and a solid understanding of microservices architecture and API design.
• Practical experience with React and TypeScript, building modern, responsive user interfaces with strong attention to frontend performance and usability.
• Hands-on experience with AWS, Docker, and Kubernetes, and CI/CD implementation using GitHub Actions, Jenkins, GitLab, or similar tools, along with infrastructure deployment and environment management experience.
• Strong knowledge of relational databases such as PostgreSQL, MySQL, or SQL Server.
• 6-8 years of software engineering experience.
• At least 1-2 years of practical Generative AI experience.
• Strong Python + React + Cloud background, with proven deployments to production.
• Ability to work across the full technology stack independently.

Nice to have

• Experience with NoSQL and vector databases.
• Experience building enterprise AI copilots or intelligent assistants.
• Experience with Model Context Protocol (MCP) and AI tool integrations.
• Experience integrating with collaboration platforms such as Microsoft Teams, Jira, ServiceNow, or similar enterprise tools.
• Familiarity with AI observability, evaluations, and monitoring frameworks.

Details

• Location: Eli Lilly, Bengaluru, India.
• Position type: Full-Time, Level R2-3.
• Travel: 0%-10%.
• Sponsorship: not supported.