Software Engineer, Applied AI- Evals
Core
Build APIs, data models, and UIs for a platform that helps frontier AI labs and enterprises evaluate model performance, manage benchmarks, and analyze failures.
Role type
Senior full-stack software engineer (AI evals platform)
Builds
APIs, data models, UIs, dataset registries, and failure analysis tools for an AI evaluation platform
Domain
AI/ML evaluation, benchmarking, and developer tools
Deliverable
production ML models
Required skills
Full-stack development, Python/Go/TypeScript, React, data-heavy product building, API design, database management, product ownership
Preferred skills
LLM evals, benchmarks, AI developer tools, B2B developer products, startup experience
Technologies
Python, Go, TypeScript, React
Responsibilities
Build APIs and data models for model evaluation, launch and manage APEX benchmarks, develop failure analysis features, create dataset registries and versioning, build customer onboarding flows, collaborate with customers on pilots
Seniority
Senior, hands-on IC
