About the Role :
We're seeking experienced Machine Learning Engineers and Software Engineers with ML experience to design and build high-quality RL training environments for LLM agents. As an RL Environment Engineer, you'll create diverse machine learning tasks that challenge and improve language models, working with minimal supervision to deliver consistent, quality outputs.
What You'll Do :
Design and build tasks
for machine learning domains that target specific language models and 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 their limitations
Hit the ground running
with minimal onboarding time
What We're Looking For :
Strong machine learning background
through coursework, previous work experience, or personal projects
Python fluency : you write clean, efficient Python code regularly
Heavy LLM user
who understands current model capabilities and failure modes through daily hands-on experience
Self-directed and creative . You can generate novel ML task ideas in your domain without constant guidance
High responsibility and integrity . You deliver quality work consistently and meet deadlines
Availability overlap
with PST 9am-5pm (minimum 3 hours required)
Work Details : Location :
Remote
Type : Contractor
Time Commitment :
40 hours a week. Must have at least 3 hours of overlap with PST business hours (9am-5pm)
Machine Learning Engineer • Kanpur, Uttar Pradesh, India