About the Team

Evaluation at Simile presents unusual engineering challenges. Our models predict distributions of human behavior, and the ground truth used to evaluate them can be noisy and heterogeneous. You will partner closely with Evals, Modeling, Product Engineering, and Data Operations to turn complex methods and inputs into systems that are reproducible, scalable, and useful for model development and business decisions.

About the Role

As a Member of Technical Staff in Evals Engineering, you will build the systems that enable Simile to evaluate whether our simulations of human behavior are accurate, trustworthy, and improving over time.

You will work across data and evaluation infrastructure, evaluation execution workflows, backend services, automation, and internal tooling. Your initial focus will include streamlining how evaluations are run across models; strengthening evaluation versioning, data models, and access controls; and automating customer validations, survey operations, and human data workflows.

In this role, you will:

• Build evaluation execution infrastructure: Develop the services, pipelines, and orchestration needed to run evaluations efficiently across datasets, model versions, populations, and use cases.
• Strengthen evaluation data systems: Design relational schemas, versioning, provenance, permissions, and quality controls that make evaluation results reproducible and trustworthy.
• Automate validation and data collection: Partner with Evals and Data Operations to streamline customer validations, survey deployment, response ingestion, and the integration of new ground truth.
• Build human data workflows: Create labeling and review tools that enable external experts and operators to contribute high-quality judgments to evaluation campaigns.
• Develop evaluation tooling: Build interfaces that help teams manage evals, compare models, investigate results, and identify regressions.

Requirements
Must Haves

• Strong Engineering Fundamentals: Several years of experience building and maintaining production-quality software, with sound judgment in system design, testing, debugging, and maintainability.
• Data and Systems Experience: Experience building backend services, data pipelines, automation workflows, and relational data models.
• End-to-End Execution: Ability to work across data, backend, and interface layers and take ambiguous projects from technical design through deployment and adoption.
• Evaluation Judgment: Strong intuition for what makes evaluation infrastructure reliable, including versioning, provenance, reproducibility, holdout integrity, noisy ground truth, and meaningful model comparisons.
• ML and LLM Fluency: Familiarity with modern model-development and evaluation workflows sufficient to partner effectively with modeling and evaluation researchers.
• Product and User Judgment: Ability to build clear, efficient tools for researchers, engineers, data operators, and other expert users.
• Ownership and Communication: A track record of independently driving important technical work and collaborating effectively across engineering, research, and operations.

Nice to Haves

We do not expect one person to have all of these. We are hiring a team with complementary strengths.

• Model-Evaluation Infrastructure: Experience building LLM or ML evaluation systems, benchmark platforms, regression suites, experiment-tracking tools, or model-quality dashboards.
• Research and Internal Tools: Experience developing technical surfaces for ML engineers, researchers, data scientists, or operations teams.
• Human Data Systems: Experience with labeling platforms, expert-review workflows, LLM-as-judge systems, grader calibration, or other human-in-the-loop evaluation methods.
• Data-Collection Automation: Experience automating surveys, experiments, customer-data ingestion, or other human data collection workflows.
• Statistical Fluency: Comfort reasoning about sampling error, uncertainty, calibration, confidence intervals, and distributional metrics.
• Sensitive Data and Access Controls: Experience designing permissions, auditability, and data-governance systems for human or customer data.
• Agentic Engineering: Experience using modern AI coding tools to accelerate development while independently testing and validating their output.

You might be a great fit if you have worked in LLM evals, applied ML research, data science, research engineering, human data, market research, UXR, polling, behavioral science, computational social science, or behavioral economics. You might also be a recent graduate or self-directed builder with unusually strong taste in evaluation, statistics, and AI tools.

You do not need to match every bullet. If you do not perfectly see yourself in this JD but believe you would be exceptional at building the measurement layer for behavioral simulation, we would love to hear from you.

Compensation & Benefits

At Simile, we provide competitive compensation packages that include base salary, equity, and comprehensive benefits.

• Salary Range: $200,000 - $400,000 USD
  
  • Note: Final offers are based on experience, specialized skills, interview performance, and relevant training.
• Equity: Grants are available for eligible roles, subject to board approval.
• Health & Wellness: Comprehensive medical, dental, and vision coverage.
• Time Off: Flexible time off policies to support work-life balance.

Our Process

We prioritize thoughtful conversations and clear examples of past work. Our hiring journey is designed to help both sides align on fit, working style, and expectations.

Reapplication Policy: To ensure a fair and thorough evaluation for all applicants, Simile observes a 90-day waiting period before reconsidering candidates for the same role.