Research Scientist, APEX Benchmarks

📋 Description

• Benchmark design for new APEX benchmarks
• Dataset design and grading rubrics at scale
• Establish measurement rigor and reporting standards
• Collaborate with academics and industry partners
• Translate results into narrative for stakeholders
• Work with data ops, product, and strategy to productionize

🎯 Requirements

• Background in evaluation, NLP, or benchmarking
• Ability to identify informative measurements
• Strong statistical rigor in sampling and analysis
• Hands-on coding to build eval harnesses
• Clear communication with technical and non-technical audiences
• Comfort with ambiguity and fast-moving teams

🎁 Benefits

• Bi-annual performance bonus structure
• Generous equity grant vested over 4 years
• Relocation bonus up to $15k
• Housing bonus up to $10k
• Monthly meals stipend $1.5k
• Free Equinox membership