Time per task: 5 hours for trainers and 1.5 hours for reviewers
Engagement: Project-based โ paid per approved task
Commitment: ~15 hours per week
Location: Fully remote
Youโll need: Hands-on expertise in at least one of Python, Java, Rust, Go, C++, or TypeScript
Your tasks: Build challenging coding problems from real repositories, with reproducible environments and verifiers
Role Title: Software Engineer
Role Type: Contractor (~15 hrs a week)
Location: Remote
Youโll create Reinforcement Learning Environments that test a modelโs ability to solve real software engineering problems: tracking down subtle bugs, building non-trivial features, refactoring, and optimizing performance. Each task means defining the problem, building a reproducible environment, and writing a reference solution.
Scope of Work
Create realistic, challenging coding tasks for frontier AI models, drawn from repositories you know well.
Design problems that require real engineering skill โ subtle bugs, non-trivial features, meaningful performance work โ not lookup or boilerplate.
Build a reproducible environment for each task.
Write deterministic verifiers that accept correct solutions across different valid implementations, while rejecting incorrect, incomplete, or hard-coded approaches.
Provide a reference solution showing how the task can be solved.
Flag tasks that turn out to be ambiguous or unverifiable rather than submitting them.
Preferred Qualifications
Significant hands-on expertise in at least one of: Python3, Java, Rust, Go, C++, or TypeScript.
Deep understanding of algorithms, data structures, and software engineering principles.
Proven ability to debug complex systems, resolve bugs, and deliver effective optimizations.
Experience with large codebase refactoring and legacy system modernization.
Track record of delivering high-impact features from conception through delivery.
Strong documentation and communication skills to articulate technical concepts clearly.
Interest in AI and its technical challenges โ previous AI experience not required.
Compensation Structure
Compensation is output-based; experts are paid per task that meets the project specifications. The time required may vary depending on your experience and workflow.
Start Timeline & Availability
We typically fill roles within 48 hours and are looking for experts ready to jump in right away. If selected, we expect you to start your first tasks within 24โ48 hours of completing onboarding.
How the selection process works
Apply and complete the screening questions
Complete the AI interview for this role โ itโs how your expertise gets in front of the client
Profile review
Onboarding โ our Talent Ops team will get you set up
Originally posted on Himalayas
Communication
Delivery
Remote work
Pay
$50 โ $100 / hour
Estimated take-home pay
Explore gross pay after typical payroll taxes for a work location.
Illustrative estimate only; assumes a standard employee profile and may omit benefits, pensions, credits and local rules. Regional and city-specific tax applies only where the selected calculator supports it; other results are country-level. Salary and location are sent only when you calculate: Paysums for supported regions, or WorthOf for wider country coverage. Confirm with an official payroll or tax source before making decisions.
Visa sponsorship and relocation: not stated in the ad.
JobCheckPoint never asks candidates to pay, and genuine employers shouldn't either. If this job asks you for money (registration, training, visa or equipment fees), don't pay. Report it below.