Remote RL Environment Engineer for LLM Tasks

Careerflow.ai; United States; Remote; USD 83,000 - 131,000; Part time

Job summary

Careerflow.ai is seeking experienced ML/Software Engineers to design and build RL training environments for LLM agents, delivering diverse tasks with minimal supervision.

This remote contractor role requires 40 hours per week and overlap with PST hours. Strong Python skills, deep ML background, and hands-on experience with large language models are essential for delivering high-quality outputs and reliable task generation.

Qualifications

• Strong ML background demonstrated by coursework, prior work, or personal projects.
• Proficient Python coding with clean, efficient style.
• Extensive daily use of LLMs and understanding model capabilities and failure modes.
• Self-directed with a track record of generating novel ML task ideas.
• High responsibility and integrity with consistent delivery and deadlines.

Responsibilities

• Design and build tasks for ML domains targeting language models and specific difficulty distributions.
• Iterate rapidly on task designs based on customer feedback with 24-hour turnaround times.
• Create diverse, challenging scenarios that test language model capabilities and expose limitations.
• Hit the ground running with minimal onboarding and rapid contribution.

Skills

Strong ML background

Python fluency

Heavy LLM user

Self-directed and creative

High responsibility and integrity

PST overlap availability

Job description

Careerflow.ai is seeking experienced ML/Software Engineers to design and build RL training environments for LLM agents, delivering diverse tasks with minimal supervision.

This remote contractor role requires 40 hours per week and overlap with PST hours. Strong Python skills, deep ML background, and hands-on experience with large language models are essential for delivering high-quality outputs and reliable task generation.