RL Environments Engineer

Company Description

Huzzle connects world-class experts with AI labs and enterprises through innovative solutions. The company leverages an AI-powered recruitment platform to source and skillfully vet talent across various domains. Huzzle's approach ensures high-quality professionals tailored to meet the needs of cutting-edge technological environments. By maintaining rigorous standards, Huzzle enables organizations to access exceptional talent efficiently and effectively.

What you'll do

You will design and build realistic engineering tasks and environments that train and evaluate LLMs. Depending on your strengths, you may focus more on production ML systems or more on performance and low-level optimization - both are valuable here.

Responsibilities

Design and build MLE/SWE environments and diverse tasks.

Target a specified language model and satisfy the required difficulty distribution.

Deliver high quality tasks.

Requirements

• Strong Python/JS/Rust/Go/Java/C++ (engineering-quality, not notebook-only).
• Hands-on LLM/GenAI work in production: you've shipped and operated real systems (not wrapped an API and called it AI).
• Strong product/engineering ownership: comfortable building, fixing, and scaling end-to-end pipelines.
• Docker + production mindset (debugging, reliability, iteration speed).

Strong signals (nice-to-have, big plus)

• Experience designing environments/tasks for RL and/or evaluations.
• Experience in high-stakes or regulated domains (e.g., healthcare, finance, fraud/risk, safety-critical systems).
• ML systems experience: CI/CD, monitoring, evaluation harnesses, MLOps, scalable pipelines.
• Systems depth: Performance/infra optimization, distributed systems.
• Exposure to RL / bandits / agentic systems (not required, but a strong signal).

Not a fit if

• You're primarily a prompt engineer without strong ML/engineering foundations.
• You're a research-only / academic-only profile with little or no shipping/production ownership.
• You've only built in notebooks or rely heavily on managed AutoML tools.