Senior Staff Engineer: AI Agents & Evaluation Infrastructure

Perplexity; Seattle (WA); Vor Ort; USD 180.000 - 260.000; Vollzeit

Zusammenfassung

Perplexity in Seattle is hiring a senior software/ML engineer to build enterprise evaluation environments and automated graders for agents, with the goal of improving reliability, latency, and cost across complex workflows.

You will design robust backend systems, run experiments, and collaborate with cross‑functional teams to advance model routing, tool use, and evaluation infrastructure in production.

Qualifikationen

• Requires 5+ years of software or machine learning engineering experience.
• Strong system design and backend programming skills.
• Hands-on experience building or improving LLM applications or agents; cross-team initiatives.

Aufgaben

• Build realistic enterprise evaluation environments and evaluation infrastructure.
• Develop automated graders to measure agent performance on complex workflows.
• Analyze failures and ship improvements to tools, routing, and execution strategies.

Kenntnisse

Software Engineering

Machine Learning Engineering

Backend Development

Python

Go

Rust

System Design

LLM Applications

AI Agents

Evaluation Infrastructure

Benchmark Design

Automated Grading

Tool Use

Model Routing

Inference Efficiency

Statistical Analysis

Jobbeschreibung

Perplexity in Seattle is hiring a senior software/ML engineer to build enterprise evaluation environments and automated graders for agents, with the goal of improving reliability, latency, and cost across complex workflows.

You will design robust backend systems, run experiments, and collaborate with cross‑functional teams to advance model routing, tool use, and evaluation infrastructure in production.