Research Engineer (Reinforcement Learning)

Highlights

• Build post-training for voice and text agents operating over long horizons.
• Own environments, verifiers, and evaluations that releases must clear.
• Ship models into production and keep improving them on real usage.

What they offer

• Competitive salary and equity package
• Health, dental, and vision benefits
• Flexible vacation policy

Ideal candidate

Strong Python engineer who has shipped models from data to production and treats data quality as the product. Pragmatic about GPUs and training tradeoffs, designs against reward hacking, and thrives collaborating remotely.

Requirements

• Strong Python engineer
• Have carried a model from raw data through to production
• Treat data as the product: coverage, diversity, leakage
• Assume a model will exploit a weak reward, and design against it
• Comfortable with GPUs and honest about their limits
• Know when to train, and when not to
• Comfortable working collaboratively in a remote environment