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

Perplexity; New York (NY); Presencial; USD 150 000 - 190 000; Tempo integral

Resumo da oferta

Perplexity is seeking a seasoned software/ML engineer to construct enterprise-grade evaluation environments, task suites, and graders for measuring agent performance on complex workflows. You will diagnose failures and push improvements across tools, skills, models, and routing to increase reliability while reducing latency and cost.

The role requires deep expertise in backend development, system design, and hands-on experience with LLM applications or agents.

Qualificações

• Requires 5+ years of software or machine learning engineering experience.
• Strong backend and system design skills with hands-on ML tooling experience.
• Experience building or improving LLM applications or agents.

Responsabilidades

• Build realistic enterprise evaluation environments, evaluation infrastructure, task suites, and graders.
• Diagnose agent failures and ship improvements to tools, skills, models, routing, and execution strategies to boost task success.

Conhecimentos

Software Engineering

Machine Learning Engineering

Backend Development

Python

Go

Rust

LLM Applications

AI Agents

Evaluation Infrastructure

Benchmark Design

Automated Grading

System Design

Model Routing

Inference Efficiency

Statistical Analysis

Cross-Functional Leadership

Descrição da oferta de emprego

Build realistic enterprise evaluation environments, evaluation infrastructure, task suites, and graders to measure agent performance on complex workflows. Diagnose agent failures and ship improvements to tools, skills, models, routing, and execution strategies that increase task success and reliability while reducing latency and cost.

Requirements: Requires 5+ years of software or machine learning engineering experience, strong backend and system design skills, and hands-on experience building or improving LLM applications or agents. Candidates should bring deep expertise in at least one relevant area, strong experimental judgment, and a record of leading complex initiatives through production adoption.

Key Skills: Software Engineering, Machine Learning Engineering, Backend Development, Python, Go, Rust, LLM Applications, AI Agents, Evaluation Infrastructure, Benchmark Design, Automated Grading, System Design, Model Routing, Inference Efficiency, Statistical Analysis, Cross-Functional Leadership