Senior Backend Engineer - Evaluation & Orchestration

Hcompany; Paris; Hybrid; EUR 70,000 - 110,000; Full time

Job summary

Hcompany is hiring for a backend engineer to build and run the evaluation framework behind its AI benchmarks. You will work on orchestration, runtimes, and observability to ensure reliable, fast, and cost-efficient runs across 50+ benchmarks now and up to 100–200 soon.

The role involves collaborating with researchers and forward deployed engineers to automate results and support product decisions. Expect 3.5 hours of interviews and a hybrid Paris posting with occasional London travel.

Qualifications

• 5+ years of backend development with production Python at the core.

Responsibilities

• Integrate benchmarks and ensure the evaluation framework operates reliably and efficiently.
• Define standards for benchmark entry and implement checks to enforce them.
• Schedule and monitor evaluation runs to optimize cluster utilization.
• Produce reproducible results across trials to support release decisions.
• Work with various stacks as benchmarks evolve, including potentially browser extensions or desktop environments.
• Interview and collaborate with researchers and forward deployed engineers to gather requirements and automate results.

Skills

Backend development

Python

Kubernetes

REST APIs

Databases

Observability

Tools

PostgreSQL

Grafana

Datadog

Docker

Playwright

Job description

Hcompany is hiring for a backend engineer to build and run the evaluation framework behind its AI benchmarks. You will work on orchestration, runtimes, and observability to ensure reliable, fast, and cost-efficient runs across 50+ benchmarks now and up to 100–200 soon.

The role involves collaborating with researchers and forward deployed engineers to automate results and support product decisions. Expect 3.5 hours of interviews and a hybrid Paris posting with occasional London travel.