colours
app
radaremprego

Expert Talent Pool, Agents and Reinforcement Learning

Clera · advertises as Himalayas, Human Resources, Expert Talent Pool
Hoursnot stated in the ad
Contractfreelance
Salary80-200 USD/hourwork out the netas stated in the ad
not stated in the adwork mode
posted 2026-11-20 ·

In short AI

Remote, hourly-paid project in human-data work for AI, focused on agents and reinforcement learning: designing environments, verifiers and evaluation of agent behaviour. Lasts from one week to several months.

Description

Role
Design reinforcement learning environments (Python, Docker, state spaces, tool integrations and scoring mechanisms); build verifiers and reward functions; translate business workflows (ERP, CRM, finance, operations) into measurable scenarios; integrate tools and REST APIs and build test harnesses with pytest; lead agent demonstration programmes and set quality standards for trace collection; grade and repair agent trajectories and mentor contributors.
Requirements
  • At least 5 years in software engineering, QA automation, machine learning, reinforcement learning, business systems or operations, with hands-on agent or RL data work
  • Strong Python skills and experience building tools or services others rely on
  • Experience designing environments, verifiers, reward functions or test harnesses
  • Hands-on experience with agent or RL data (demonstrations, trajectory grading, trace collection, computer-use demos)
  • Experience with REST APIs and Docker
Preferred
  • leading or reviewing data, evaluation or demonstration programmes; modelling ERP or CRM workflows; degree in computer science, engineering or related field
Conditions
Contract: independent, per project
Salary: 80 to 200 USD per hour, depending on project, field and experience level; paid for hours worked
Hours: not stated
Location: remote
Benefits
none stated

About the Role

Join a network of experienced technical contributors working on paid AI human-data projects focused on agents and reinforcement learning. You will design training environments, build evaluation systems, and assess agent behavior as projects become available.

What You'll Do

  • Design reinforcement learning environments, including Python and Docker setups, state spaces, tool integrations, and scoring mechanisms.

  • Build verifiers and reward functions that reliably evaluate agent performance and resist gaming.

  • Translate real-world business workflows in areas such as ERP, CRM, finance, and operations into measurable scenarios.

  • Integrate tools and REST APIs, and build test harnesses using frameworks such as pytest.

  • Lead agent demonstration and computer-use programs, setting quality standards for trace collection.

  • Grade and repair agent trajectories, and mentor contributors on evaluation practices.

What We're Looking For

  • 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 RL data work.

  • Strong Python skills and experience building tools or services that others rely on.

  • Experience designing environments, verifiers, reward functions, or test harnesses to evaluate software or agent behavior, using tools such as pytest, Playwright, Selenium, or Gymnasium-style environments.

  • Hands-on experience with agent or RL data, such as demonstrations, trajectory grading, trace collection, or computer-use demos.

  • Experience integrating REST APIs and using Docker.

  • Experience leading or reviewing work on data, evaluation, or demonstration programs is valued, as is expertise modeling workflows in business systems such as ERP or CRM platforms.

  • A degree in computer science, engineering, or a related field is relevant.

Compensation & Benefits

Compensation is $80 to $200 per hour, depending on project, field, and experience level. Pay is based on hours worked. Visa sponsorship information was not provided.

Location

Remote. Projects typically last from one week to several months.

Originally posted on Himalayas

How to apply

Apply on the original ad ↗

Prepare your application

A cover letter and a short pitch for this job, written from your profile, and what to learn next.

Sign in and create your profile from your CV. It is private: we share it with no one.

Something wrong or unlawful in this ad? Report it

It stays visible while we review it. We decide within 7 days (anything clearly unlawful, such as a scam, sooner) and tell you the outcome and why.

Similar jobs

Salary compared ⓘ

This jobMedian?4 179 €
2 763 €6 116 €

83 jobs · Systems analysts · remote

see the best paid →

Training for this job

Languages AI

Published on (1)

First seen on 20 Nov, 21:48