Sr. Staff Software Engineer - AI Chat

About the role

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.

Responsibilities

• 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.
• 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. No hand-offs.
• 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.
• Implement MCP integrations that connect agents to enterprise data sources and tools.
• Use agentic coding tools like Claude Code and GitHub Copilot as a daily force multiplier — not a novelty.
• Shape how agents are registered, discovered, and invoked on Cortex — defining the framework that the rest of the organization builds on.
• 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

Preferred Qualifications

• 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

Qualifications

• Experience with real-time systems: WebSockets, SSE, event-driven architectures, or workflow orchestration
• Familiarity with MCP, A2A, or emerging AI interoperability protocols
• Experience with real-time systems: WebSockets, SSE, event-driven architectures, or workflow orchestration
• Familiarity with MCP, A2A, or emerging AI interoperability protocols
• Experience with real-time systems: WebSockets, SSE, event-driven architectures, or workflow orchestration
• Familiarity with MCP, A2A, or emerging AI interoperability protocols

Benefits

• Eligibility to participate in a company-sponsored 401(k)
• Pension
• Vacation benefits
• 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
• Well-being benefits (e.g., employee assistance program, fitness benefits, and employee clubs and activities)

Pay

The anticipated wage for this position is $126,000 - $224,400

Schedule

Full-time equivalent employees also will be eligible for a company bonus (depending, in part, on company and individual performance).