Staff ML Engineer, Agent Evaluation Platform

Moveworks

Mountain View (CA)

Hybride

USD 180 000 - 240 000

Plein temps

Il y a 3 jours
Soyez parmi les premiers à postuler

Obtenez une réponse de cet employeur

Votre CV et votre lettre de motivation, adaptés exactement à ce que l’employeur recherche.

Passez les filtres ATS

Résumé du poste

Moveworks is seeking a Staff Software Engineer to own the agent evaluation platform. You will design the judgement layer for scoring multi-step agent actions across enterprise systems, calibrate against human labels, and create signals that drive improvements.

The role spans eval orchestration at scale, agent observability, and stateful simulation, with back-end work in Python/Go, OpenTelemetry, and contract-tested simulations in a high-scale enterprise context.

Qualifications

  • 8+ years building production backend or infrastructure systems.
  • Strong in Python or Go (ideally both).
  • Experience designing and operating systems that handle real traffic at scale.
  • Comfort turning non-deterministic agent behavior into a measurable signal.
  • Experience in at least 3 of the listed areas (distributed systems, orchestration, observability, concurrency, data pipelines, gRPC/protobuf).

Responsabilités

  • Eval orchestration at scale: run multi-turn agent scenarios end-to-end and manage environments.
  • Scheduling, retries, high-concurrency execution, and run isolation at production data sizes.
  • Versioned specs, datasets, and run-to-run comparisons as core operations.
  • Consolidate evals onto a single orchestration service with a single source of truth.
  • Establish reliability floors and an SLO for the harness.
  • Enable self-serve evals without bespoke integrations.
  • Lead OpenTelemetry-native observability for the agent platform.
  • Define span data model for agent trajectories and cross-run diffing.
  • Maintain trace context across async boundaries and sessions.
  • Preserve prompts/completions through pipelines and provide debugging surfaces.
  • Build stateful simulators with hermetic per-run setups.
  • Create fakes for enterprise systems and contract-testing mocks.
  • Lay the foundation for using eval signal to optimize the agent.

Connaissances

Distributed systems
Orchestration
Observability internals
Concurrent programming
Data pipelines
Python
Go
gRPC
Protobuf
OpenTelemetry

Outils

OpenTelemetry
gRPC
Protobuf

Description du poste

Moveworks is seeking a Staff Software Engineer to own the agent evaluation platform. You will design the judgement layer for scoring multi-step agent actions across enterprise systems, calibrate against human labels, and create signals that drive improvements.

The role spans eval orchestration at scale, agent observability, and stateful simulation, with back-end work in Python/Go, OpenTelemetry, and contract-tested simulations in a high-scale enterprise context.

Obtenez votre examen gratuit et confidentiel de votre CV.

ou faites glisser et déposez votre fichier ici.

Similar jobs

Postes similaires à comparer

Senior AI Evaluation Systems Engineer
Senior AI Evaluation Systems Engineer

Servicenow • Santa Clara (CA)

Sur place
USD 180 000 - 320 000
Staff ML Evaluation & Calibration Engineer
Staff ML Evaluation & Calibration Engineer

Servicenow • Mountain View (CA)

Sur place
USD 180 000 - 260 000
Tech Lead for Agent Evaluation Platform
Tech Lead for Agent Evaluation Platform

Servicenow • Mountain View (CA)

Hybride
USD 180 000 - 260 000
Staff Software Engineer, Agent Eval Platform
Staff Software Engineer, Agent Eval Platform

Servicenow • Santa Clara (CA)

Sur place
USD 180 000 - 320 000
Staff Software Engineer — Scale AI Evaluation & Orchestration
Staff Software Engineer — Scale AI Evaluation & Orchestration

Servicenow • Mountain View (CA)

Sur place
USD 180 000 - 240 000
Senior ML Engineer: Agentic Evaluation & Reward Modeling
Senior ML Engineer: Agentic Evaluation & Reward Modeling

Servicenow • Santa Clara (CA)

Hybride
USD 150 000 - 230 000
Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)
Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)

Perplexity • Seattle (WA)

Sur place
USD 180 000 - 260 000
Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)
Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)

Perplexity • New York (NY)

Sur place
USD 150 000 - 190 000
Senior ML Evaluations Platform Engineer - Remote
Senior ML Evaluations Platform Engineer - Remote

Artificial.Agency • États-Unis

Hybride
USD 85 000 - 127 000
Staff Software Engineer, Enterprise AI Evaluation
Staff Software Engineer, Enterprise AI Evaluation

Perplexity • San Francisco (CA)

Sur place
USD 180 000 - 240 000