Senior Software Engineer - AI Agent Platform
Core
Build and operate the production runtime platform that executes, orchestrates, and monitors AI agents for travel and expense workflows.
Role type
Senior IC backend/platform engineer (AI agent runtime)
Builds
Reliable runtime infrastructure, abstractions, and observability for AI agent execution and tool calling
Domain
Generative AI / Distributed Systems / Cloud Infrastructure
Deliverable
production ML models | infrastructure
Required skills
TypeScript, Node.js, NestJS, distributed systems design, production debugging, cloud infrastructure (AWS), distributed caching (Redis), S3, observability (logs/metrics/tracing/SLOs), API design, software architecture
Preferred skills
LLM APIs, agentic patterns, multi-provider routing, Kafka, Kubernetes, chaos engineering, internal developer platforms
Technologies
TypeScript, Node.js, NestJS, AWS, Redis, S3, Kafka, Kubernetes, Grafana
Responsibilities
Own and evolve the production runtime for AI agent execution and orchestration; Design platform capabilities for tool calling, streaming, state management, and long-running workflows; Build resilient integrations with multiple LLM providers and implement fallback strategies; Ensure platform availability during external outages; Create end-to-end observability for AI requests including token usage and cost; Lead investigation of complex production issues across code, infrastructure, and agent behavior; Improve platform scalability and resource efficiency; Build reusable APIs and abstractions for agent developers; Strengthen platform quality through load testing and failure injection; Mentor engineers on building reliable production AI systems
Seniority
Senior, hands-on IC
