Member of Technical Staff, Research Engineering

Turn reinforcement learning research into working systems

Build environments and training infrastructure that connect experimental ideas with scalable implementation. The work covers task design, data generation, model improvement, and rigorous evaluation.

• Architect self contained reinforcement learning environments with reward functions, verifiers, and evaluation logic.
• Design episode pipelines and multicomponent training processes for reproducible experiments.
• Build automated and synthetic data generation systems while maintaining data quality.
• Integrate AI assisted grading, validation, quality checks, and feedback processes.
• Fine tune and improve open source models using generated datasets and custom training strategies.
• Establish benchmarks for capability, robustness, and data quality across tasks.
• Contribute to the release and analysis of internal and external evaluations.

Required technical experience

Deep reinforcement learning knowledge, including environment design and training dynamics, is required. You should have a strong record of building and scaling RL systems, pipelines, or experimentation frameworks.

Automation and data generation skills are essential, including practical synthetic data pipelines. Familiarity with automated evaluation, model validation, and quality assurance workflows is also required.

You should have experience fine tuning and evaluating open source machine learning models and communicate technical decisions clearly in writing.

Helpful background

Experience publishing benchmarks, evaluations, or research artifacts would be useful. Familiarity with evaluation ecosystems and infrastructure for large scale RL experiments is also relevant.

The role suits collaborative work in a research environment with frequent iteration and changing technical questions.

Compensation and benefits

This is a full time position with a national annual base salary range of $180,000–260,000. Employees are eligible for equity and may receive performance based compensation according to role and policy.

Benefits include up to 100% reimbursement of health insurance premiums, paid time off, and a 401(k) with an employer match. The package is described for a remote first workforce, without a specific work location stated.

AI tools assist candidate screening and assessment while human decision making is retained.