Tech Lead, Agent Eval Platform (AI)

Location: Required in office in Mountain View, California, United States

Company

Moveworks provides an agentic AI assistant platform that connects employees with enterprise systems through natural language, backed by ServiceNow following its December 2025 acquisition.

What you will do

• Lead development of an evaluation orchestration runtime for multi-turn agent scenarios, including scheduling, retries, isolation, validation, scoring, and run comparison.
• Build production-scale workflow infrastructure with high-concurrency execution, versioned datasets, reports, reliability targets, and self-service evaluation runs.
• Lead the transition to OpenTelemetry-native observability, including trajectory span models, trace propagation, prompt and completion capture, fault attribution, and cross-run diffing.
• Develop stateful simulation environments for enterprise systems such as ITSM, HR, knowledge bases, and inventory, with persistent datastore-backed changes.
• Build hermetic simulators, contract-testing mocks, sandbox environments, and LLM-driven or deterministic user simulators.
• Establish evaluation signals that can be used to optimize and train AI agents, not only measure them.

Requirements

• 10+ years of experience building production backend or infrastructure systems.
• Experience in at least three areas: distributed systems, workflow orchestration, observability internals, concurrent and asynchronous programming, data-intensive pipelines, or gRPC/protobuf interface design.
• Strong Python or Go skills; experience with both is preferred.
• Experience designing and operating systems handling real traffic at scale.
• Ability to technically lead engineers and deliver projects end to end, with strong communication and collaboration skills.
• Comfort making non-deterministic systems measurable and working through ambiguous, novel problems.

Culture & Benefits

• Work within a distributed organization using assigned work personas based on the role and work location.
• Join an AI-focused business backed by ServiceNow’s global scale.
• Work on applied AI evaluation problems involving real, stateful enterprise-system actions.
• Access an inclusive and accessible employment environment with reasonable accommodations available.