Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)
Perplexity21 days ago
Base Salary
$220k - $405k/yr
Responsibilities
- Build realistic enterprise evaluation environments with connected applications, datasets, user roles, permissions, and reproducible multi-step workflows.
- Own evaluation infrastructure, task suites, automated graders, regression gates, and launch-readiness signals for agent and platform changes.
- Analyze agent trajectories and production failures, identify root causes, and ship improvements across agent harnesses, tools, skills, and models.
- Develop reusable skills and improve tool descriptions, schemas, and result handling for better tool selection, workflow execution, and error recovery.
- Build model-selection and routing strategies that balance task quality, latency, reliability, and cost.
- Improve agent efficiency through context management, skill loading, caching, and execution strategies.
- Lead cross-team initiatives from architecture through production adoption and mentor engineers.
Requirements
- 5+ years of software engineering or machine learning engineering experience owning complex production systems through design, deployment, and operation.
- Strong system design skills and experience building reliable, scalable infrastructure for experimentation, evaluation, or data-intensive applications.
- Strong proficiency in a backend language such as Python, Go, or Rust, with the ability to work across a multi-language production stack.
- Hands-on experience building, evaluating, or improving LLM-based applications or agents involving tool use and multi-step workflows.
- Deep expertise in evaluation infrastructure, agent harnesses and tool interfaces, realistic multi-system test environments, or model selection and inference efficiency.
- Strong experimental and statistical judgment in task selection, success criteria, failure diagnosis, and distinguishing real improvements from noise.
- Sound technical judgment balancing quality, latency, reliability, and cost, with a record of translating findings into shipped improvements.
- Track record of leading ambiguous cross-team initiatives, setting technical direction, and raising engineering quality through mentorship.
Categories
About Perplexity
Perplexity builds an AI-powered answer engine for web and mobile and an enterprise product, Perplexity Computer, for AI-driven workflows across tools and apps. The company monetizes through individual subscriptions (Perplexity Pro) and enterprise plans. Founded in 2022 and headquartered in San Francisco, it operates as a privately held company.