Callosum
Visit websiteAgent Runtime & Systems - Member of Technical Staff
Salary not disclosedOnsite
- Engineering
- London
- Full time
- Today
About the role
Callosum is building a software orchestration layer to unify heterogeneous compute for AI systems. This role owns the runtime and programming model for long-running agent systems, focusing on durable execution, distributed scheduling, and observability. You will develop core software to make agent workflows reliable, debuggable, and efficient across a full-stack infrastructure.
Responsibilities
- Design and build stateful, asynchronous agent runtimes across distributed environments
- Define event histories, checkpoint and resume semantics, and recovery from partial failure
- Build traces, replay, time-travel debugging, and hierarchical tracing across model calls and tools
- Develop clear Python APIs, libraries, and DSLs with stable extension points
- Design scheduling, placement, backpressure, resource accounting, and sandboxing for secure tool execution
- Develop tooling for trajectory collection, performance profiling, and failure attribution
Required skills
- Distributed systems
- Python
- Rust
- C++
- Go
- Durable workflows
- Actor systems
- Workflow engines
- API design
Nice to have
- Ray
- Temporal
- Kafka
- Erlang
- BEAM
- PyTorch
- JAX
- TensorFlow
- ML systems
Benefits
- Competitive Salary
- Equity
- Private healthcare
- Visa sponsorship
- Relocation benefits
About the Company
Callosum is the Intelligent Systems Company building infrastructure that unifies heterogeneous compute across the full stack. They are focused on co-evolving models, workflows, and silicon to deliver inference tailored to every workload.