About Bespoke Labs

Bespoke Labs is an applied AI research lab pioneering data curation and RL environment curation for the modern agentic world. Our mission is to enable everyone to post-train models, and we are going to do this by addressing the key bottlenecks: good quality data and RL environments.

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.

About the Role

As a member of our technical staff, you will work on building our infrastructure for RL environment curation as well data curation. This involves also building the app (backend, frontend, and CLI)) that's necessary for interfacing with environment engineers (i.e. those who create RL environments) and our eval platform. Ideal candidates are problem solvers who can own idea-to-launch end-to-end.

What you will do

1. Build scalable data pipelines for ingesting, validating, and storing reinforcement learning environments from various sources. Create processing systems to analyze environment quality, difficulty levels, and suitability for different AI training scenarios

2. Build intuitive dashboards for environment engineers to upload, manage, and monitor their RL environments. Create visualization tools for environment performance metrics, success rates, and training progress. Implement collaborative features allowing teams to share environments, annotations, and feedback.

3. Work closely with the team to understand their specific needs for environment curation and evaluation. Create APIs and SDKs that allow researchers to programmatically interact with the platform

4. Contribute to RL environment curation.

Who you are

1. At least 2 years of experience in backend development, particularly in distributed systems.

2. Proficiency in languages like Python and experience with cloud platforms (GCP, AWS, etc.).

3. Have experience designing robust CI/CD pipelines, automated testing, observability, and monitoring.

4. Able to show samples of frontend you have built in the past.

5. Ability to design systems that scale to handle large volumes of data and complex workflows.

6. A self-starter who is excited about working on hard technical problems in AI and data-centric platforms.

7. Past experience with open-source projects is a great plus.

8. No prior AI experience necessary.

Location is either in Mountain View, CA (Hybrid) or India (remote).