Staff Software Engineer (Agent Evaluation Platform)

Join Moveworks, a leading AI company that empowers employees to get instant answers to their questions. As a Staff Software Engineer, you will be responsible for building the judgement layer of our agent evaluation platform, which is crucial for improving the performance of our AI agents. You will work on applied machine learning, focusing on the methodology of evaluating AI agents in real-world enterprise environments.

Missions

• Concevoir et mettre en œuvre la couche de jugement de la plateforme d'évaluation des agents, y compris les rubriques, les juges et la méthodologie.
• Diriger le développement d'un environnement de simulation d'utilisateur pour exécuter des scénarios d'agents multi-tours de bout en bout.
• Établir un service d'orchestration unique pour consolider les évaluations qui fonctionnent actuellement comme des flux de travail uniques.

Profil recherché

- Distributed systems: idempotency, delivery guarantees, isolation, and - unusually central here - determinism and reproducibility

- Data-intensive pipelines: high-volume ingest, schema evolution, sampling and retention trade-offs

- Orchestration and workflow runtimes: DAG execution, scheduling, retries, backfills, high-concurrency job systems (Temporal, Airflow, Argo, or something you built yourself)

- Observability internals as a builder, not just a user: OpenTelemetry SDKs and collectors, semantic conventions, span context propagation, high-cardinality trace data

- GRPC/protobuf service and interface design

- Experience in at least 3 of these: