Staff Engineer, Agent Runtime & Systems

Callosum Technologies Ltd.; Greater London; Hybrid; GBP 120,000 - 170,000; Full time

Benefits offered by this job

Competitive salary

Equity

Healthcare

Visa sponsorship

In-office London

Job summary

Callosum Technologies Ltd. in London is hiring for a senior engineer to own the runtime and programming model for long-running agent systems. You will focus on durable execution, checkpointing, replay, distributed scheduling, and secure tool execution.

You’ll develop core software that makes agent workflows reliable, debuggable, and reproducible as the model and tools evolve. This high-leverage role operates across the full stack with a hands-on, problem-solving mindset.

Qualifications

• Experience with distributed systems and durable workflows.
• Designing libraries, frameworks, runtimes, or DSLs used by others.
• Strong Python expertise and systems language skills (Rust/C++/Go).
• Hands-on debugging across APIs and distributed infrastructure.

Responsibilities

• Design and build stateful, asynchronous agent runtimes across distributed environments.
• Define event histories, checkpoint/replay semantics, and recovery from partial failures.
• Develop traces, time-travel debugging, and hierarchical tracing across components.
• Create clear Python APIs, libraries, and DSLs with stable extension points.
• Address scheduling, resource accounting, and secure tool execution at scale.
• Build tooling for performance profiling, experiment comparison, and regression detection.

Skills

Distributed systems

Python

Systems languages

API design

Debugging

Tools

Ray

Temporal

Kafka

PyTorch

JAX

TensorFlow

Job description

Callosum Technologies Ltd. in London is hiring for a senior engineer to own the runtime and programming model for long-running agent systems. You will focus on durable execution, checkpointing, replay, distributed scheduling, and secure tool execution.

You’ll develop core software that makes agent workflows reliable, debuggable, and reproducible as the model and tools evolve. This high-leverage role operates across the full stack with a hands-on, problem-solving mindset.