Member of Technical Staff, RL Research & Environments
Magic · San Francisco
CHECKED 8H AGO
Frontier labonsite$275k–$550k
At a glance
Highlights
- Design reward signals and training environments for long-horizon RL iteration.
- Build evaluation frameworks that surface long-context failure modes.
- Own data and environment systems connecting product goals to capability gains.
What they offer
- Equity
- 401(k) plan with 6% salary matching
- Health, dental and vision insurance for you and dependents
- Unlimited paid time off
- Relocation stipend
Ideal candidate
A hands-on research engineer who owns data and environment systems end-to-end and obsesses over data quality and rigorous evaluation to drive measurable long-context capability gains.
Requirements
- Strong software engineering fundamentals
- Experience building or operating large-scale data or ML systems
- Ability to design and interpret experiments that measure model behavior changes
- Comfort working at the intersection of ML, data systems, and infrastructure
- Strong attention to data quality and evaluation rigor
- Track record of owning experimental or production systems end-to-end
- visa sponsorship
- Visa sponsorship available
Lab profile
About Magic
Building safe AGI that automates research and code generation to accelerate progress.
Known for
- Frontier-scale pre-training
- Domain-specific RL
- Ultra-long context
- Inference-time compute