Research Scientist

bareinsights; Los Angeles (CA); On-site; USD 110,000 - 150,000; Full time

Job summary

bareinsights is seeking a Research Scientist to bridge data design and model development for AI training datasets. You will shape evaluation frameworks, define data structures, and run experiments that drive model alignment across finance, code, and enterprise domains.

Based on your background, you will contribute to quantitative measures of dataset quality and collaborate with lab researchers to translate training objectives into concrete data specifications. On-site in Los Angeles.

Qualifications

• Undergraduate or master’s research background; strong preference for candidates who have not yet completed a PhD.
• Prior experience with evals or benchmarking — through academic research, a competing data company, or an internship at an RL environment company.
• Genuine curiosity about how data structure, selection, and quality drive model behavior.
• Ability to design lightweight experiments, move quickly, and extract actionable insights from noisy results.
• Strong quantitative instincts and familiarity with LLM training pipelines, RLHF, RLVR, or evaluation methodology.
• Comfort working across domains including finance, software engineering, and policy.
• Software engineering experience is a meaningful plus — technical depth is valued here.

Responsibilities

• Design data structures that expose meaningful model failure modes across domains such as finance, code, and enterprise workflows.
• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines.
• Model annotator behavior and run targeted experiments to improve model capabilities.
• Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment.
• Partner with lab research teams to translate training objectives into concrete data and evaluation specifications.

Job description

About the Role

This role sits at the intersection of data design and model development at a Series A AI training data company that works directly with frontier AI labs. Research Scientists here design the datasets and evaluation frameworks that shape how cutting‑edge models are trained and measured — work with direct, visible impact on model behavior at scale.

What You’ll Do

• Design data structures that expose meaningful model failure modes across domains such as finance, code, and enterprise workflows.

• Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines.

• Model annotator behavior and run targeted experiments to improve model capabilities.

• Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment.

• Partner with lab research teams to translate training objectives into concrete data and evaluation specifications.

What We’re Looking For

• Undergraduate or master’s research background; strong preference for candidates who have not yet completed a PhD.

• Prior experience with evals or benchmarking — through academic research, a competing data company, or an internship at an RL environment company.

• Genuine curiosity about how data structure, selection, and quality drive model behavior.

• Ability to design lightweight experiments, move quickly, and extract actionable insights from noisy results.

• Strong quantitative instincts and familiarity with LLM training pipelines, RLHF, RLVR, or evaluation methodology.

• Comfort working across domains including finance, software engineering, and policy.

• Software engineering experience is a meaningful plus — technical depth is valued here.

Compensation & Benefits

Base salary range: $110,000–$150,000 USD annually. Compensation is performance‑driven with significant upside tied to the impact of your work. Visa sponsorship is not available.

Location

On‑site in Los Angeles, CA. Candidates are also considered from New York City, NY and San Francisco, CA.