Senior Software Engineer

About the role

H builds computer-use agents and the models behind them. This role involves building and maintaining the evaluation framework that ensures these models are reliable, fast, and efficient. You will work closely with researchers and forward-deployed engineers to scale the framework as the number of benchmarks grows.

Responsibilities

• Provide integration support for researchers and forward-deployed engineers to bring new benchmarks into the framework.
• Set standards for benchmark integration and build automated checks to enforce them.
• Manage scheduling and observability to optimize cluster capacity and prevent job queuing.
• Ensure reproducible results across trials to support release decisions.
• Collaborate with customers to identify measurement needs and automate the flow of results into internal harnesses.

Required skills

• Backend development
• Python
• Test tooling
• QA tooling
• Evaluation tooling
• Distributed systems
• Kubernetes
• AWS
• REST APIs
• GraphQL
• Relational databases
• Non-relational databases
• Message queues
• Metrics
• Tracing

Nice to have

• LLM quality measurement
• Agent development
• Docker
• Temporal
• Dask
• FastAPI
• PostgreSQL
• Grafana
• Datadog
• Playwright

About the Company

H builds computer-use agents and the models behind them. Developers use these tools through a managed API, and forward-deployed engineers integrate them into enterprise workflows.