Agentic AI Harness Architect
ServiceNow8 hours ago
Base Salary
$201k - $352k/yr
Responsibilities
- Set the technical vision and architecture for the Moveworks agentic AI harness, including planning, tools, context, memory, critique, reflection, adaptation, and recovery.
- Invent and prototype algorithms that improve agent performance on complex, long-horizon tasks with less supervision.
- Design model-agnostic abstractions combining foundation models, specialized agents, enterprise tools, policies, and deterministic workflows.
- Develop agent memory and learning approaches using execution traces, user feedback, and task outcomes while preserving security and privacy.
- Create benchmarks and evaluation methods for tool-use correctness, plan quality, task completion, groundedness, policy compliance, latency, and cost.
- Explore iterative planning, ReAct-style execution, self-critique, reflection, test-time computation, multi-agent coordination, and verifier-guided reasoning.
- Build high-fidelity prototypes, identify investment-worthy ideas, and guide successful approaches toward production.
- Partner with Agentic Systems, Search, Relevance, ML Infrastructure, Product, and Security teams.
- Remain hands-on with code and experiments while influencing architecture, mentoring senior engineers, and raising technical standards.
Requirements
- Deep expertise in machine learning or artificial intelligence with strong systems judgment and end-to-end product architecture skills.
- Meaningful work on AI agents, reasoning and planning, tool use, coding agents, conversational systems, reinforcement learning, or related areas.
- Experience translating ambiguous research questions into prototypes, measurable hypotheses, and durable technical direction.
- Strong understanding of tradeoffs among model capability, context, memory, latency, cost, reliability, and system complexity.
- Experience designing evaluations and benchmarks for probabilistic systems based on task outcomes.
- Excellent programming skills and ability to work directly in modern machine learning and agent stacks; Python expertise is expected.
- Evidence of cross-team technical leadership, roadmap influence, and ability to guide senior engineers without formal authority.
- Typically 8 or more years of relevant industry or research experience, or an equivalent record of exceptional technical and research impact.
- Preferred: master’s degree or PhD in computer science, machine learning, artificial intelligence, or a related field, or equivalent practical experience.
- Preferred: published research, influential open-source work, or widely adopted systems involving agents, language models, reasoning, evaluation, or human-agent interaction.
- Preferred: experience with new agent architectures, core AI products, enterprise identity and authorization, auditability, privacy, policy enforcement, safe tool execution, and production systems.
Benefits
- Base pay of $201,300 - $352,300, plus equity when applicable, variable or incentive compensation, and benefits.
- Health plans including flexible spending accounts, a 401(k) plan with company match, ESPP, matching donations, flexible time away, and family leave programs.
- Regular employee role with a required-in-office work persona in North America and Canada.
- Compensation varies by geographic work location and individual qualifications.
Tech Stack
Categories
AI Research
About ServiceNow
ServiceNow builds a cloud platform for enterprise digital workflows, covering IT service management, customer service, HR service delivery, security operations, and operations management, plus tools for custom app development. It sells subscription SaaS to large organizations and public-sector agencies to automate processes and connect data across systems. Founded in 2004 and headquartered in Santa Clara, California, ServiceNow is a public company listed on the NYSE under the ticker NOW.