Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)
Perplexity9 hours ago
Base Salary
$220k - $405k/yr
Responsibilities
- Build realistic enterprise evaluation environments with connected applications, representative datasets, user roles, permissions, and complex multi-step workflows.
- Own evaluation infrastructure, task suites, automated graders, regression gates, and launch-readiness signals for agent, model, connector, tool, skill, and harness changes.
- Analyze agent trajectories and production failures, identify root causes, and ship improvements across the agent harness, tools, and skills.
- Develop reusable skills and improve tool descriptions, schemas, and result handling so agents can execute workflows and recover from errors effectively.
- Build and evaluate model-selection and routing strategies that balance quality, latency, reliability, and cost.
- Improve efficiency through context management, skill loading, caching, and execution strategies.
- Partner with AI Research, Connectors, and Platform teams to translate experimental results into production adoption and measurable gains.
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, including tool use and multi-step workflows.
- Deep expertise in evaluation infrastructure, benchmark design, automated grading, agent harnesses, tool interfaces, reusable workflow skills, realistic simulations, model routing, inference efficiency, context management, or caching.
- Strong experimental and statistical judgment, including defining representative tasks and meaningful success criteria, diagnosing failures, and distinguishing improvements from noise.
- Sound technical judgment balancing task quality, latency, reliability, and cost, with a record of translating evaluation findings into shipped improvements.
- Experience leading ambiguous cross-team initiatives from architecture through production adoption, setting technical direction, and mentoring engineers.
- The employer encourages applications from candidates who do not meet every qualification and values demonstrated impact, ownership, and initiative.
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.