Sr. Staff Software Engineer - AI Chat

Eli Lilly and Company • Indianapolis, IN

1d

About The Position

At Lilly, we unite caring with discovery to make life better for people around the world. We are a global healthcare leader headquartered in Indianapolis, Indiana. Our employees around the world work to discover and bring life-changing medicines to those who need them, improve the understanding and management of disease, and give back to our communities through philanthropy and volunteerism. We give our best effort to our work, and we put people first. We’re looking for people who are determined to make life better for people around the world. ChatNow is how Lilly talks to AI. Every day, tens of thousands of employees open ChatNow to get work done — asking questions, running analyses, invoking specialized agents. It's the front door to Cortex, Lilly's enterprise AI platform. And it needs to be fast, intuitive, and relentlessly reliable. We're looking for a Senior Staff Software Engineer to own the technical direction and delivery of ChatNow's core platform: the routing engine that matches intent to the right agent, the integration layer that connects a growing ecosystem of AI capabilities, and the experience layer that makes it all feel effortless. You'll set the technical bar for one of Lilly's most visible AI products — and ship code that the entire company uses every day. What You'll Do You'll define the architecture and drive implementation of ChatNow's conversation routing engine — the system that takes a user's intent and connects it to the right AI agent, model, or workflow. You'll own the agent integration layer, designing how ChatNow connects to Lilly's expanding network of specialized AI agents on Cortex. You'll build streaming chat interfaces in React and TypeScript, backed by scalable services that handle thousands of concurrent sessions with low latency across multiple AI providers. You'll own features end to end. Design, build, test, deploy, monitor. No hand-offs. You'll operate ChatNow on Cortex and Hangar — Lilly's enterprise Kubernetes platform — instrumented with LGTM observability so you can see exactly how routing, latency, and agent performance behave in production. You'll integrate LLM capabilities through Cortex's model gateway, supporting multi-model routing with fallback and load balancing. You'll implement MCP integrations that connect agents to enterprise data sources and tools. And you'll use agentic coding tools like Claude Code and GitHub Copilot as a daily force multiplier — not a novelty. This is AI-native engineering at staff level. You'll shape how agents are registered, discovered, and invoked on Cortex — defining the framework that the rest of the organization builds on. You'll make technical decisions that ripple across teams, mentor engineers, and raise the standard for what production AI software looks like at Lilly.

Requirements

• 10+ years of professional software engineering experience, with demonstrated technical leadership at scale
• 5+ years in TypeScript/JavaScript, Python and Go (with ability to use AI coding tools proficiently), architecting and building production web applications with React or equivalent
• 5+ years experience designing RESTful or GraphQL APIs at scale Deep hands-on experience with Kubernetes — not just deploying, but operating, debugging, and tuning
• Strong CI/CD and GitOps practices
• Bachelor's degree in Computer Science, Software Engineering, or a related field

Nice To Haves

• Experience integrating LLM APIs into production — streaming, function calling, tool use
• Hands-on work with conversational AI systems: routing, intent classification, context management, or multi-agent orchestration
• Experience with real-time systems: WebSockets, SSE, event-driven architectures, or workflow orchestration
• Familiarity with MCP, A2A, or emerging AI interoperability protocols
• Active use of agentic coding tools in your daily workflow
• A track record of shipping user-facing products with high reliability and polish
• Experience setting technical direction across multiple teams or workstreams

Responsibilities

• define the architecture and drive implementation of ChatNow's conversation routing engine
• own the agent integration layer, designing how ChatNow connects to Lilly's expanding network of specialized AI agents on Cortex
• build streaming chat interfaces in React and TypeScript, backed by scalable services that handle thousands of concurrent sessions with low latency across multiple AI providers
• own features end to end. Design, build, test, deploy, monitor
• operate ChatNow on Cortex and Hangar — Lilly's enterprise Kubernetes platform — instrumented with LGTM observability
• integrate LLM capabilities through Cortex's model gateway, supporting multi-model routing with fallback and load balancing
• implement MCP integrations that connect agents to enterprise data sources and tools
• shape how agents are registered, discovered, and invoked on Cortex

Benefits

• Full-time equivalent employees also will be eligible for a company bonus (depending, in part, on company and individual performance).
• Lilly offers a comprehensive benefit program to eligible employees, including eligibility to participate in a company-sponsored 401(k); pension; vacation benefits; eligibility for medical, dental, vision and prescription drug benefits; flexible benefits (e.g., healthcare and/or dependent day care flexible spending accounts); life insurance and death benefits; certain time off and leave of absence benefits; and well-being benefits (e.g., employee assistance program, fitness benefits, and employee clubs and activities).

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees