Member of Technical Staff – Agent Runtime & Systems

About the role

We are looking for a senior engineer to own the runtime and programming model for long‑running, stateful agent systems. You will work at the core of our AI infrastructure, building reliable, debuggable and efficient execution across heterogeneous hardware.

Key responsibilities

• Design and build stateful, asynchronous agent runtimes that operate across distributed environments.
• Define event histories, checkpoint/restart semantics, deterministic reconstruction, retries, cancellations and failure recovery.
• Implement tracing, time‑travel debugging and hierarchical tracing across model calls, tools and runtime decisions.
• Develop Python APIs, libraries and DSLs with stable extension points for new tools and back‑ends.
• Design scheduling, placement, back‑pressure, resource accounting and sandboxed execution for secure tool usage at scale.

Required profile

• Strong distributed‑systems background with hands‑on experience in durable workflows, actor systems, schedulers, workflow engines, distributed databases or stream processors.
• Experience designing libraries, frameworks, runtimes or DSLs adopted by other engineers or researchers.
• Deep Python expertise plus proficiency in a systems language such as Rust, C++ or Go.
• Hands‑on debugging skills across APIs, runtimes and distributed infrastructure, with an understanding of nondeterminism and reproducibility.

Required skills

• Python
• Rust, C++ or Go
• Distributed systems, actor systems, workflow engines, distributed databases, stream processors
• API design and debugging
• Familiarity with Ray, Temporal, Kafka, Erlang/BEAM, PyTorch, JAX, TensorFlow

What we offer

• Competitive salary based on skills and experience
• Equity and ownership
• Private healthcare
• Visa sponsorship and relocation benefits
• On‑site work in our London office with dedicated tools and space