Remote Agentic AI Harness Architect

Moveworks; Mountain View, Northern (CA, KY); Hybrid; USD 201,000 - 352,000; Full time

Job summary

Moveworks is seeking an Agentic AI Harness Architect in Mountain View to set the technical vision for integrating foundation models, enterprise tools, and policies. You will prototype algorithms and memory strategies to enable agents to complete longer tasks with less supervision and higher reliability.

You will design model-agnostic abstractions and benchmarks, while collaborating with product, security, and ML teams to deliver production-ready AI automation at enterprise scale.

Qualifications

• 8+ years of industry or research experience.
• Experience turning ambiguous questions into working prototypes, measurable hypotheses, and durable technical direction.
• Strong understanding of tradeoffs among model capability, context, memory, latency, cost, reliability, and system complexity.
• Excellent programming skills and Python proficiency; production systems knowledge is valuable.
• Evidence of technical leadership across teams and roadmaps.

Responsibilities

• Set the technical vision for the Moveworks agentic AI harness, including planning, tool selection, context management, memory, critique, reflection, adaptation, and recovery.
• Invent and prototype algorithms that help agents complete longer, more complex tasks with less supervision and stronger outcome reliability.
• Design model-agnostic abstractions for combining foundation models, specialized agents, enterprise tools, policies, and deterministic workflows.
• Develop approaches for agent memory and learning from execution traces, user feedback, and task outcomes while preserving enterprise security and privacy.
• Create rigorous benchmarks and evaluation methods for tool-use correctness, plan quality, task completion, groundedness, policy compliance, latency, and cost.
• Explore methods such as iterative planning, ReAct-style execution, self-critique, reflection, test-time computation, multi-agent coordination, and verifier-guided reasoning.
• Build high-fidelity prototypes, identify the ideas that merit investment, and work with platform and product teams to define a practical path to production.
• Partner across Agentic Systems, Search, Relevance, ML Infrastructure, Product, and Security to connect agent intelligence with enterprise knowledge, permissions, and actions.
• Remain hands-on with code and experiments while influencing architecture, mentoring senior engineers, and raising the technical bar across the organization.

Skills

AI agents

Reasoning & planning

Tool use

Coding agents

Python

Leadership

Production systems

Education

Master's degree or PhD in CS/ML/AI

Job description

Moveworks is seeking an Agentic AI Harness Architect in Mountain View to set the technical vision for integrating foundation models, enterprise tools, and policies. You will prototype algorithms and memory strategies to enable agents to complete longer tasks with less supervision and higher reliability.

You will design model-agnostic abstractions and benchmarks, while collaborating with product, security, and ML teams to deliver production-ready AI automation at enterprise scale.