Agentic Harness Engineer
On-site · Zürich, Zurich, Switzerland
Job Summary
Agentic Harness Engineer role focused on powering DeepJudge's agentic harness across critical features and evaluating stability and quality of frontier-model deployments. Responsibilities include owning the agentic harness, building and running end-to-end evals from design to instrumentation, improving agent quality through code and prompting, and influencing model and launch decisions based on agent quality. Collaborate with Legal Engineering, Product, and Customer Success to prioritize harness improvements; stay current on LLM/GenAI trends and translate insights into best practices. Requires a Master’s degree in CS or equivalent, strong backend programming skills (Python/Rust/Go/C++), experience building large LLM-based applications, and ability to design meaningful eval frameworks; familiarity with agentic SDKs and LLM-system evaluation is a plus. Location is on-site in Zurich, Switzerland, with a collaborative, growth-oriented environment.
Required Qualifications
- Master’s degree in Computer Science or a related field, or equivalent practical experience
- Proficiency in one or more backend programming languages such as Python, Rust, Go, or C++
- Ability to evaluate agentic systems and design meaningful eval frameworks
- Strong interest in GenAI and frontier models
- Experience building large applications based on LLMs
- Nice to have: Experience with agentic SDKs
- Nice to have: Familiarity with evaluation of LLM-based systems
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.