About the Role
Mercor’s evals platform helps frontier labs and enterprises understand how their models perform on real work. Labs use it to decide what to train next, and enterprises use it to decide which models and agents to trust. It runs evals at scale, grades every result and explains why a model fails. The team also runs APEX, Mercor's family of benchmarks built with domain experts to measure how well frontier models do professional work in fields like law, finance and consulting. Its public leaderboard ranks the latest models, and its results appear in model cards across the industry.
As a Software Engineer on the Evals product team, you will build the scorecards, failure reports and dataset views that help customers turn eval runs into decisions. You will solve hard problems in scale, grading accuracy and reproducibility, while keeping the product simple to use.
This role grows with the platform, from evals into post-training and new product areas. You will help turn the failures we find into data that improves models.
What You'll Do
Build the product customers use to evaluate models: Ship the APIs, data models and UI that help customers run evals, compare models and share scores.
Own APEX launches: Run every new frontier model on APEX and publish correct, defensible results to the public leaderboard.
Explain why models fail: Build failure analysis that helps customers see where their models fail, with each pattern linked to the exact steps that went wrong.
Make benchmarks easy to find and manage: Build dataset views, registries and versioning that help customers find the right benchmark or bring their own.
Take customers from first login to self-serve: Build onboarding, roles, key management and usage views that help new teams run evals on their own.
Work directly with customers: Join pilots with labs and enterprises and turn what they need into the roadmap.
What We Are Looking For
Bachelor's Degree in Computer Science or a related field
Strong full-stack skills in a modern backend language (Python, Go or TypeScript) and a frontend framework such as React
A track record of owning product features end to end, from idea to production
Strong product sense that starts from what the user needs
Experience building data-heavy products: data models, APIs and views over large volumes of results
Excellent written and verbal communication with engineers, researchers and customers
Comfort with ambiguity and a habit of shipping iteratively
Experience with LLM evals, benchmarks or AI developer tools is a plus
Startup experience or experience building B2B developer products is a plus
Benefits
Generous equity grant vested over 4 years
Health, dental, and vision insurance
401(k) with company match
Unlimited paid vacation and sick days
Parental leave for birthing and non-birthing parents
Free mental health services
$200 monthly wellness reimbursement
$1.5K monthly meal stipend
$200 monthly laundry reimbursement
Free Equinox membership
Up to $15K relocation bonus
Mercor is an Equal Opportunity Employer and is committed to providing equal opportunity to all employees and applicants. Mercor does not discriminate based on actual or perceived race, color, creed, religion, national origin, ancestry, citizenship status, age, sex or gender (including pregnancy, childbirth, related medical conditions and lactation), gender identity or gender expression, sexual orientation, marital status, military service and veteran status, disability, protected medical condition as defined by California or local law, genetic information, or any other characteristic protected by applicable federal, California, or local laws and ordinances. Further, Mercor prohibits discrimination, harassment, and retaliation based on any combination of protected characteristics. This Policy applies to all areas of employment, including recruitment, hiring, training, promotion, compensation, benefits, discipline, termination, and all other privileges, terms, and conditions of employment. This Policy and the law prohibit employment discrimination against any employee or applicant based on any legally protected status.
