Agent Runtime & Systems - Member of Technical Staff
$101,000–$192,000 year
On-siteLondon, England, United Kingdom
Job Summary
Design and build stateful, asynchronous agent runtimes across distributed environments, defining event histories, checkpoint semantics, and recovery from partial failure. Develop traces for time-travel debugging and hierarchical tracing across model calls, tools, and state changes. Build scheduling, placement, and sandboxing mechanisms for secure tool execution at scale while creating Python APIs and DSLs with stable extension points. Engineer observability tooling for trajectory collection, performance profiling, and failure attribution across runtime versions. This role tackles complex systems challenges in durable execution and distributed scheduling, requiring deep Python expertise and proficiency in systems languages like Rust or Go. Based in London, this position reports to the General Capabilities Team.
Required Qualifications
- Strong distributed systems background with hands-on experience in durable workflows, actor systems, schedulers, workflow engines, distributed databases, or stream processors
- Experience designing a library, framework, runtime, or DSL that other engineers or researchers adopted
- Deep Python expertise plus proficiency in a systems language such as Rust, C++, or Go - and the instinct to move between abstraction layers when it matters
- Hands-on debugging skills across APIs, runtimes, and distributed infrastructure - with a practical understanding of nondeterminism, side effects, and reproducibility
Desired Qualifications
- Experience building a production-grade runtime, compiler, workflow engine, distributed training system, database, debugger, or orchestration platform
- Meaningful contributions to systems such as Ray, Temporal, Kafka, Erlang/BEAM, PyTorch, JAX, TensorFlow, or comparable projects
- Strong API design judgement, open-source collaboration, and disciplined approaches to testing, versioning, compatibility, and reproducibility
- Experience in ML systems or large-scale inference and training
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.