Senior Backend Engineer – Evaluation Framework & Benchmarks

H Company; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

H is hiring to build and operate an evaluation framework that runs benchmarks across web apps, desktop environments and command lines. You will help researchers and forward deployed engineers integrate benchmarks, enforce input standards, and ensure observability so runs are fast, reliable and cost-efficient.

This role emphasizes end-to-end engineering—from cluster tuning to new benchmark integrations—while working closely with researchers, product teams, and a VP of Engineering.

Qualifications

• 5+ years in backend development with production Python at the core.
• Experience building test, QA or evaluation tooling used by other teams.
• Operated distributed systems on Kubernetes in a public cloud (AWS helps).
• Experience building end-to-end systems including APIs (REST/GraphQL) and external integrations.

Responsibilities

• Integration support for researchers and forward deployed engineers bringing benchmarks into the framework.
• Set the standard for how benchmarks enter the framework and build checks to enforce it.
• Schedule and monitor workloads to maximize cluster efficiency without idle time.
• Ensure reproducible results across trials so that releases are data-driven.
• Handle diverse stacks as Benchmarks evolve, from clusters to browser extensions or desktop environments.
• Engage with customers to understand measurement needs and automate results into harnesses.

Skills

Python

Backend development

Distributed systems

Kubernetes

REST/GraphQL

Testing/QA tooling

Observability/Monitoring

Benchmark integration

Tools

Kubernetes

AWS

Docker

PostgreSQL

Grafana

Datadog

Playwright

Selenium

Job description

H is hiring to build and operate an evaluation framework that runs benchmarks across web apps, desktop environments and command lines. You will help researchers and forward deployed engineers integrate benchmarks, enforce input standards, and ensure observability so runs are fast, reliable and cost-efficient.

This role emphasizes end-to-end engineering—from cluster tuning to new benchmark integrations—while working closely with researchers, product teams, and a VP of Engineering.