Systems Engineer @ Dedalus Labs

Mission

Dedalus Labs is an AI research neolab building infrastructure for AI agents.

We’re building the persistent compute layer that powers the next generation of autonomous software. Our platform spans virtualization, distributed systems, storage, networking, orchestration, and low-level runtime infrastructure. Every millisecond, every sys-call, every scheduling decision matters.

We’re looking for systems engineers who enjoy understanding computers all the way down.

You might be a fit if you

• Think abstractions are useful because you understand what’s underneath them.

• Care about latency, throughput, memory usage, and tail performance.

• Enjoy debugging problems that take days to understand and minutes to fix.

• Believe reliability is a feature.

• Think distributed systems are fun rather than frightening.

• Get excited reading kernel commits, infrastructure blogs, or systems papers.

• Have strong opinions about operating systems, virtualization, networking, or storage.

• Like making difficult systems feel simple.

• Measure before optimizing, then optimize relentlessly.

• View performance engineering as product engineering.

• Believe the best infrastructure disappears into the background.

• Are high agency and fiercely independent.

• Say how things ought to be built, then build them.

• Are a competitive teammate with a heart of gold.

• Are hungry to learn, improve, and reflect deeply on feedback.

• Go above and beyond in everything you do.

What you’ll build

• Distributed infrastructure for large-scale agent workloads.

• Virtualization and sandboxing systems.

• Persistent compute and storage primitives.

• Scheduling, orchestration, and reliability systems.

• Runtime infrastructure for long-running AI agents.

• Internal developer platforms and tooling.

• Production systems operating under real-world scale, latency, and reliability constraints.

Representative Projects

You might find yourself working on problems like:

• Building a distributed storage layer for persistent agent state.

• Improving sandbox startup latency from seconds to milliseconds.

• Designing scheduling systems that efficiently allocate compute across thousands of concurrent agents.

• Developing virtualization and isolation technologies for secure multi-tenant workloads.

• Profiling bottlenecks across networking, storage, scheduling, and runtime layers.

• Building developer infrastructure that makes deploying and operating AI agents dramatically simpler.

What we look for

• Fluency in Rust (preferred), Go, C/C++, or similar systems languages.

• Strong software engineering fundamentals.

• Good understanding of operating systems, distributed systems, or networking concepts.

• Ability to reason about performance, reliability, concurrency, and debugging.

• Comfortable navigating large systems with many moving parts.

• High agency and excellent engineering judgment.

• Strong communication and collaborative instincts.

Nice-to-have

• Experience with Kubernetes or modern cloud infrastructure.

• Experience building distributed systems in industry, research, or open source.

• Familiarity with distributed storage systems.

• Understanding of consistency models and consensus.

• Experience with virtualization, containers, hypervisors, or Firecracker.

• Kernel, operating systems, or low-level runtime experience.

• Contributions to systems-focused open source projects.

• Experience with performance engineering and systems optimization.

• Background in systems research, networking, databases, distributed computing, or related fields.

• Experience operating production infrastructure at scale.

Taste

You know the difference between software that merely works and software that feels inevitable.

You care about elegant abstractions, good engineering judgment, and building systems that other engineers love using.

Logistics

• In person in San Francisco.

• Relocation support available.

• We sponsor visas.

• Competitive salary and meaningful equity.

• Meals and office benefits included.

Tips

The first thing we look at is your GitHub.

Show us systems you’ve built. Open-source contributions. Research. Infrastructure projects. Kernel patches. Homelabs. Performance investigations. Technical writing.

We care far more about what you’ve built than how many years you’ve been building.