Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)

Details

The Enterprise Agent Evals & Efficiency team makes Perplexity's agents better at completing real work across enterprise connectors, tools, and data. The team helps agents choose the right tools, use the right context, and complete complex workflows reliably while reducing time and compute. This role owns the improvement loop: defining successful work, building evaluations, diagnosing agent failures, and shipping changes that improve outcomes.

This is a hands-on engineering role with end-to-end ownership, from building realistic enterprise evaluation environments to shipping improvements across the agent harness, tools, and skills. The role involves creating complex scenarios spanning connected systems, data, and permissions; identifying where agents struggle; and improving the tools agents call, the skills they follow, the context they receive, and the models they use. The role works with AI Research, Connectors, and Platform teams to improve task success, latency, and cost per successful task.

Responsibilities

• Build realistic enterprise evaluation environments spanning connected applications, representative datasets, user roles, permissions, complex multi-step workflows, and reproducible system state.
• Own evaluation infrastructure, task suites, and automated graders that measure how well agents complete enterprise work, calibrated against human judgment and grounded in end-to-end outcomes.
• Analyze agent trajectories and production failures, identify root causes, and ship improvements across the agent harness, tools, and skills to improve task success and reliability.
• Develop reusable skills and improve tool descriptions, schemas, and result handling so agents can select the right tools, execute workflows correctly, and recover from errors with fewer unnecessary calls.
• Build and evaluate model-selection and routing strategies that match tasks to the appropriate model and effort level while balancing quality, latency, reliability, and cost.
• Improve agent efficiency through context management, skill loading, caching, and execution strategies that reduce wasted tokens and cost per successful task without compromising quality or safety.
• Build regression gates and launch-readiness signals for model, connector, tool, skill, and harness changes, and validate that evaluation gains translate into improved production outcomes.

Requirements

• 5+ years of software engineering or machine learning engineering experience, with a track record of owning complex production systems from design through deployment and operation.
• Strong system design skills, including 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 effectively 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 at least one of the following areas:
  • Evaluation infrastructure, benchmark design, and automated grading.
  • Agent harnesses, tool interfaces, and reusable skills for complex workflows.
  • Realistic test environments or simulations spanning multiple systems, datasets, permissions, and stateful workflows.
  • Model selection, routing, and inference efficiency, including context management and caching.
• Strong experimental and statistical judgment, including choosing representative tasks, defining meaningful success criteria, diagnosing failures, and distinguishing real improvements from noise.
• Sound technical judgment in balancing task quality, latency, reliability, and cost, with a track record of translating evaluation findings into shipped improvements.
• A track record of leading ambiguous, cross-team initiatives from architecture through production adoption, setting technical direction, and raising engineering quality through mentorship.
• Applicants are encouraged to apply even if they do not meet every qualification. Demonstrated impact, deep ownership, and the initiative to turn ambiguity into results are valued.

Benefits

Full-time U.S. employees receive a comprehensive benefits program including equity, health, dental, vision, retirement, fitness, commuter and dependent care accounts, and more. Full-time employees outside the U.S. receive a comprehensive benefits program tailored to their region of residence.