2 days ago
Remote, WorldwideSenior
Responsibilities
- Design reinforcement-learning environments with Python, Docker, state spaces, tool integrations, and scoring mechanisms.
- Build verifiers and reward functions that evaluate agent performance reliably and resist gaming.
- Translate ERP, CRM, finance, and operations workflows into measurable scenarios.
- Integrate tools and APIs and build evaluation test harnesses.
- Lead agent demonstration and computer-use programs and set quality standards for trace collection.
- Grade and repair agent trajectories and mentor contributors on evaluation practices.
Requirements
- At least 5 years of experience in software engineering, QA automation, machine learning, reinforcement learning, business systems, or operations paired with hands-on agent or reinforcement-learning data work.
- Strong Python skills and experience building tools or services used by others.
- Experience designing environments, verifiers, reward functions, or test harnesses for software or agent behavior.
- Hands-on experience with agent or reinforcement-learning data, including demonstrations, trajectory grading, trace collection, or computer-use demonstrations.
- Experience integrating REST APIs and using Docker.
- Experience leading or reviewing data, evaluation, or demonstration programs is valued.
- Expertise modeling workflows in ERP or CRM platforms is valued.
- A degree in computer science, engineering, or a related field is relevant.
Benefits
- Remote work arrangement.
- Paid project-based engagements typically lasting from one week to several months.
- Compensation is based on hours worked.
