Member of Technical Staff, Research Engineering

This is a fully remote position, open to applicants in New York.

📋 Description

• Design self-contained reinforcement-learning environments for intricate real-world tasks.

• Create reward functions, verification mechanisms, evaluation logic, and complementary components for the environment.

• Organize environments to ensure dependable experimentation and quantifiable model advancements.

• Convert research goals into structured RL workflows.

• Guarantee that environments are reproducible, verifiable, and conducive to iterative model development.

• Develop and scale episode pipelines along with multi-component training workflows.

• Construct reproducible experimentation frameworks for reinforcement-learning research.

• Establish systems for executing, monitoring, and analyzing extensive training experiments.

• Enhance reliability and efficiency within RL training infrastructure.

• Create automated systems for generating synthetic data.

• Develop AI-powered evaluation and quality assurance systems for grading, validation, and feedback.

• Set up automated feedback mechanisms to enhance training data and model quality.

• Design verification systems that differentiate strong model performance from superficially convincing outputs.

• Fine-tune and optimize open-source reinforcement-learning and machine-learning models.

• Create benchmarking frameworks to assess capability, robustness, and data quality.

• Analyze model performance across both internal and external evaluation environments.

• Contribute to the development, publication, and interpretation of research evaluations and benchmark outcomes.

• Function across research experimentation and production-focused technical implementation.

• Adjust research priorities, evaluation systems, and experimentation processes as project demands evolve.

⛳️ Requirements

• Extensive professional or research experience in reinforcement learning.

• In-depth understanding of RL environment design, reward structures, training dynamics, and evaluation processes.

• Proven experience in building and scaling RL systems, training pipelines, or experimentation frameworks.

• Strong background in automation and synthetic data generation workflows.

• Familiarity with automated evaluation, model validation, and quality assurance systems.

• Experience in fine-tuning and assessing open-source machine-learning models.

• Excellent technical writing and communication abilities.

• Capacity to work effectively in fast-paced, research-oriented, and highly collaborative settings.

• Experience in publishing benchmarks, evaluations, or research artifacts is a plus.

• Knowledge of contemporary evaluation ecosystems and benchmarking frameworks is advantageous.

• Experience with scalable infrastructure supporting large-scale RL experimentation is highly regarded.

• Must refrain from using confidential or proprietary information belonging to any employer, client, institution, or any other third party.

🏝️ Benefits

• Fully remote position.

• Full-time commitment.

• Salary ranging from $400,000 to $800,000 per year.

• Remote consulting opportunities available across technical, evaluation, and project-based workstreams.