Research Engineer, RL Frontiers

Highlights

• Train frontier models to automate kernel, ASIC and hardware engineering tasks.
• Build RL environments rewarded by simulation and hardware measurements.
• Create benchmarks that drive real productivity and avoid reward hacking.

What they offer

• Medical, dental, and vision packages with generous premium coverage
• $500 per month credit for waiving medical benefits
• $2,500 per month housing subsidy near office
• Relocation support to San Jose
• Wellness benefits covering fitness and mental health
• Daily lunch and dinner in office
• Unlimited compute budget subject to ROI justification
• Significant equity

Ideal candidate

Entrepreneurial post-training engineer who has taken models from bad to good with scarce data and cares about making RL loops faster, cheaper, and truly useful for engineering work.

Requirements

• Hands-on post-training experience including SFT and RL with shipped models
• Track record taking a model from bad to good on a new task with scarce data
• Strong PyTorch and distributed-training engineering skills
• Understanding of RL systems to make training loops faster and cheaper
• Entrepreneurial mindset with good judgment under compute and data constraints