Job
Expert Talent Pool, Agents and Reinforcement Learning
Clera Clera offers roles in legal evaluation of AI systems and ML internship opportunities
Senior-level remote position designing and evaluating reinforcement learning environments and agent behavior for AI human-data projects. Open world-wide, with flexible and project-based focus.
At a glance
- Deadline
- Location
- Remote
- Salary
- 80 – 200 USD / hour
- Paid
- Yes
- Employment type
- Full Time
- Minimum years of experience
- 5
- Listed
About this opportunity
Clera is seeking a senior professional to join its expert network supporting AI human-data projects focused on agents and reinforcement learning. The role centers on designing training environments, evaluation systems, and assessing agent behavior as projects come in.
This is a fully remote, full-time position with projects that typically run from one week to several months. Compensation ranges from $80 to $200 per hour, depending on project scope and seniority.
You will build Python-based reinforcement learning environments, integrate tools and REST APIs, and create robust verifiers and reward functions that resist agent gaming. You’ll translate real-world business workflows into measurable evaluation scenarios and lead demonstrations and trace collection quality standards.
Strong Python experience, hands-on work with agent or RL data, and comfort with Docker, APIs, and testing tools are essential. A degree in CS or a related field is relevant.
What you get
- Hourly pay between $80 and $200
- Remote work
- Project-based engagements
- Opportunity to work on cutting-edge reinforcement learning projects
- Potential for long-term collaboration
Responsibilities
- Design reinforcement learning environments, including Python and Docker setups, state spaces, tool integrations, and scoring mechanisms
- Build robust verifiers and reward functions that resist agent gaming
- Translate business workflows into measurable evaluation scenarios (ERP, CRM, finance, operations)
- Integrate tools and REST APIs, and build test harnesses using pytest or similar tools
- Lead agent demonstrations and trace collection programs, setting standards for evaluation quality
- Grade and repair agent trajectories, mentor contributors on evaluation practices
Requirements
- At least 5 years of experience in software engineering, QA automation, ML, RL, or related fields with hands-on agent or RL data work
- Strong Python skills and experience building tools or services used by others
- Experience designing environments, verifiers, reward functions, or test harnesses for evaluating software or agents
- Hands-on experience with agent or RL data (demonstrations, trajectory grading, trace collection)
- Experience with REST APIs and Docker
- Experience leading or reviewing data, evaluation, or demonstration work is valuable
- A degree in computer science, engineering, or a related field
How to apply
- Apply through the listing or the hosted job page on Himalayas (link provided in listing)
Ready to apply?
WorkInRwanda never asks for money to apply. If anyone does, report it. Report this listing
About Clera
Clera is involved in legal and artificial intelligence work, offering roles that blend EU law expertise with AI evaluation. The listings indicate remote opportunities available worldwide and focus on senior legal professionals with EU knowledge as well as entry-level ML work.
See everything from Clera