Research Engineer

Bespoke Labs is an applied AI research lab pioneering data and RL environment curation for training and evaluating agents.

Recently, we curated Open Thoughts, one of the best open reasoning datasets used by multiple frontier labs, trained SOTA specialized models such as Bespoke-MiniChart-7B and Bespoke-MiniCheck, and taught agents to do multi-turn tool-calling with reinforcement learning.

Bespoke is uniquely positioned to capture a large market share of data and RL environment curation.

We're looking for a Research Engineer to bridge cutting-edge research with production-scale development and deployment of RL environments. You'll work at the intersection of research and engineering—collaborating with frontier labs and enterprise customers to understand their needs, then translating those insights into systematic environment creation.

This role requires both research depth and execution excellence. You'll need to understand the latest advances in agent training, communicate effectively with research teams at top labs, and build robust systems that deliver high-quality environments at scale. You're equally comfortable reading papers, prototyping novel approaches, and shipping production pipelines.

You'll work closely with both external collaborators (frontier labs, enterprise partners) and internal teams to ensure our research insights translate into valuable products that advance the state of agent training.

• Partner with frontier AI labs to understand their agent training needs and design custom environments.

• Stay current with latest research in RL, agent training, and evaluation methodologies.

• Prototype novel approaches to environment generation, curriculum design, and data curation.

• Translate academic insights into practical engineering solutions.

• Build and maintain scalable systems for creating, validating, and deploying RL environments

• Develop systematic approaches to data curation that ensure quality and diversity

• Create automated quality assurance pipelines for environment verification

• Design evaluation frameworks that measure environment effectiveness

• Work directly with enterprise customers to understand their specific agent training challenges

• Customize environment suites and benchmarks for different use cases and domains

• Provide technical guidance on best practices for agent training and evaluation

• Present research findings and product capabilities to technical stakeholders

• Scale research prototypes into production-ready systems that handle large-scale deployment

• Establish reproducible workflows and maintain high engineering standards

• Create documentation and tools that enable both internal teams and external users

• Monitor and optimize system performance as we scale environment production

• MS or PhD in Machine Learning, Computer Science, or related field, OR equivalent industry research experience

• Track record of research contributions (publications, open-source projects, or deployed research systems)

• Deep understanding of reinforcement learning, agent training, or related areas

• Ability to read and implement ideas from recent papers

• Strong Python skills and experience with ML frameworks (PyTorch, JAX, or similar)

• Experience building production systems or research infrastructure at scale

• Proficiency with cloud platforms (GCP, AWS) and distributed computing

• Systematic approach to testing, validation, and quality assurance

• Ability to use modern tools such as Claude Code effectively.

• Excellent communication skills for working with research teams and enterprise customers

• Experience translating between research concepts and practical requirements

• Ability to scope projects, set priorities, and deliver on commitments

• Comfortable presenting technical work to diverse audiences

• Understanding of what makes research artifacts valuable to users

• Experience shipping products, datasets, or tools used by others

• Attention to detail in documentation, usability, and user experience

• Customer-focused approach to problem-solving

• Hands-on experience with RL agent training or evaluation systems

• Background in data-centric AI, synthetic data generation, or dataset creation

• Publications in top ML/AI conferences (NeurIPS, ICML, ICLR, etc.)

• Previous experience in a research engineering or applied scientist role

• Contributions to widely-used datasets, benchmarks, or evaluation suites

Location: Mountain View, CA

Compensation: Competitive salary and equity

Benefits: Health coverage, and the opportunity to work directly with the world's leading AI research labs