FOUNDING AGENT SOFTWARE ENGINEER

ABOUT COBROWSER

CoBrowser is building the trust layer for the agent-native web—the secure infrastructure that lets AI agents act on a user's behalf with permission, memory, and control.

Our first product, Kontext, gives agents persistent memory and scoped access to user data—making agents smarter, more relevant, and more trustworthy over time. It's already boosting retention, engagement, and UX for real AI apps.

We're backed by a16z CSX and founded by operators from a16z, BCG, and the Ethereum Foundation. We're building the invisible rails that help agents reliably help people.

THE ROLE

As our Founding Agent Software Engineer, you'll own the scalable infrastructure that powers agent memory, context, and personalization in production.

You'll be responsible for our job queues, caching layer, and metrics systems. You'll build for performance and fault tolerance—ensuring every agent gets the right context, at the right time, under load.

You'll also lead our evaluation pipeline: creating benchmarking frameworks to measure how personalization impacts agent behavior, performance, and UX.

This is a role for a builder who thinks in terms of latency, throughput, and observability, and wants to shape the production foundations of the agent-native web.

WHAT YOU'LL DO

• • Scale our memory + auth infra with Redis, BullMQ, and background jobs
• • Build and maintain metrics pipelines to benchmark agent personalization
• • Optimize latency + throughput across sessions, users, and token usage
• • Implement caching, rate-limiting, and data freshness policies
• • Design observability and evaluation infra (Prometheus, OpenTelemetry, etc.)
• • Work closely with product and researchers to test and validate improvements

YOU MIGHT BE A FIT IF YOU:

• • Have 3–7 years experience building production backend systems
• • Are fluent in TypeScript and know your way around Redis, BullMQ, or similar queues
• • Have experience benchmarking real-time or generative systems
• • Understand session management, token auth, or personalization flows
• • Have shipped production systems under load — and debugged them at 2AM
• • Like clean abstractions but know when to ship scrappy fixes

EVEN BETTER IF YOU:

• • Have worked on infra for ML, LLM agents, or personalization at scale
• • Built devtools or monitoring for production ML/LLM systems
• • Know how to reason about caching and invalidation strategies
• • Have 0→1 startup experience or worked in high-velocity engineering teams

COMPENSATION

$150K – $200K + Meaningful Equity
Location: Munich or San Francisco (in-office)
Visa support available