AI Engineer, RL
About The Position
Taste Labs is building the data and infrastructure layer for taste, aiming to end AI slop and make AI feel right, not just correct. The company has raised $18.5M in seed funding and has many frontier labs as customers. AI has mastered objective domains but struggles with subjective judgment, such as what fits, what feels authentic, and what is truly great. Taste Labs is working to make these subjective qualities measurable, starting with design. They operate on two fronts: developing post-training data and RL environments to instill taste in frontier models, and creating context and verification tools for agents to produce more creative, on-brand, and accurate work. The role involves tackling challenging, ambiguous, and creative problems to make subjective domains verifiable.
Requirements
- Experience in building evals, RL environments, ML or post-training
- Strong backend experience
- Ability to work on ambiguous, hard, creative problems
- Team player with startup DNA: moves fast, adapts, takes ownership, and is comfortable with tasks outside of a narrow scope
Nice To Haves
- Open source contributions or personal projects
- Background at creative companies (Figma, Notion, Canva, Adobe, Runway, etc.)
- Background at companies with strong index building/crawling (e.g. Firecrawl, Brave, Luma, Pika)
- Background at data companies (Mercor, Surge, etc.)
Responsibilities
- Research different grading methods and rubrics
- Design unique tasks that can capture elements of “taste” and design capabilities
- Build agent harnesses and context layers
- Work on scalable RL infra
- Work with internal research teams on our training pipelines
- Work with the top frontier labs on how to craft environments to improve frontier models
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
