Research EngineerAt Variance, we are teaching machines to make the hardest judgment calls at scale. That means building AI agents for the high-stakes gray area of risk investigations, fraud, and identity reviews.We're a small, talent-dense team in San Francisco working on a problem at the edge of what AI systems can reliably do: making good decisions in messy, adversarial, real-world environments. We focus on building, high-consequence systems problems where the edge cases matter most.We're looking for a Research Engineer to help define how we measure and improve model quality.
You'll build the benchmarks, datasets, tooling, and evaluation loops that tell us whether our systems are actually getting better on the tasks that matter. This role sits at the center of research, product, and engineering. It is about creating rigorous, domain-specific evaluations that reflect real customer workflows, expose meaningful failure modes, and drive the next generation of model and agent improvements.You're a fit if you:Care deeply about craftsmanship and have strong opinions about model quality, measurement, and experimental rigorWant to work on core model and agent behavior, not just surface-level product metricsAre excited by the challenge of defining what "good" looks like in messy, high-stakes environmentsThink in tight loops: hypothesis, benchmark design, evaluation, failure analysis, iterationHave strong engineering fundamentals and like building robust systems around ambiguous research problemsThrive in environments where success criteria are initially underspecified and need to be sharpened through workAre willing to do the work in the trenches: reviewing outputs, grading edge cases, curating datasets, and refining tasks until the evaluation actually measures what mattersCare deeply about building systems that protect people from fraud, scams, and abuseWhat you'll doBuild proprietary benchmarks and datasets to evaluate models and model systems on fraud, identity, and risk workflowsDesign and run offline and online evals that measure model performance on real customer tasks, not just abstract benchmarksDefine quality metrics for judgment systems, including precision, calibration, consistency, abstention, and failure handlingStudy where models and agents break, and turn those failures into better evals, better datasets, and better training loopsBuild reusable evaluation tools and quality building blocks that can be used across different product surfaces and workflowsPartner closely with research, engineering, product, and design to improve system quality through rigorous experimentationHelp create a strong culture of scientific experimentation, clear measurement, and continuous iterationPush the boundary of how AI systems are evaluated in regulated, adversarial, and high-consequence environmentsWhat success looks likeWe have a clear, trusted view of how our systems perform across the workflows that matter mostOur evals predict real-world quality better than generic benchmarksWe identify meaningful failure modes earlier and improve system behavior fasterWe develop differentiated datasets, benchmarks, and quality loops that compound over timeResearch and engineering teams use your work to make better decisions about what to train, ship, and improve nextVariance becomes known for rigorous, domain-specific evaluation of judgment systemsPreferred backgroundExperience training, evaluating, or improving modern ML systemsStrong programming skills and comfort working in research-heavy codebasesExperience building benchmarks, datasets, evaluation pipelines, or quality systemsFamiliarity with LLMs, agent systems, retrieval, post-training, or adjacent areasAbility to design clean experiments and draw reliable conclusions from noisy resultsStrong engineering judgment and a bias toward buildingInterest in fraud, risk, trust and safety, compliance, or other regulated and adversarial domainsOur cultureWe believe in ownership, urgency, and craft.
We enjoy spirited debate, wild ideas, and building things we're proud of. We're fully in-person in San Francisco.What we offerCompetitive salary and meaningful equityPlatinum-level medical, dental, and vision insuranceUnlimited PTO, sick leave, and parental leaveUp to $100 per month in reimbursement for personal health and wellness expenses401(k) plan