Lead AI Engineer

Onto Innovation•Milpitas, CA

4d•$129,600 - $194,400•Onsite

About The Position

Onto Innovation is hiring a Lead AI Engineer to set the technical vision and architecture for AI in semiconductor metrology and to build and productionize AI systems that accelerate setup and troubleshooting and improve measurement quality. This hands-on technical leadership role works closely with system engineers, algorithm developers, and applications teams. It emphasizes agents grounded in real tools and data, with appropriate human oversight, and includes setting technical direction and mentoring AI and ML engineers. The role covers the full AI system lifecycle, including agent workflows for recipe and model setup, qualification, tool matching, and root-cause triage; integration with simulators, solvers, and instrument data; and retrieval grounded in fab knowledge with provenance. Systems must be designed for trust, uncertainty, auditability, and deployment in on-premises or air-gapped environments, with customer change-control requirements in mind. The role also owns evaluation practices and relevant measurement-science ML, including surrogate models, parameter inference, calibration, and uncertainty. The Lead AI Engineer establishes engineering standards, leads design and code reviews, mentors junior and mid-level engineers, and makes technical and build-versus-buy decisions. The role improves software quality and AI-assisted development practices through testing, CI/CD, analysis, security review, and validation. It translates customer fab and yield problems into agent workflows and explains outcomes to engineers. The position is designed to be on-site, with close daily collaboration in the office and occasional time at fab or customer sites.

Requirements

MS or PhD in computer science, electrical engineering, physics, applied mathematics, or equivalent hands-on experience.
At least 6 years of applied ML/AI experience in production, including at least 3 years in technical leadership, leading projects or owning technical direction of a significant AI system.
Experience defining AI strategy and system architecture and gaining adoption of a technical vision across engineering.
Hands-on experience with production LLM-based systems, including agents, tool calling, retrieval, prompt and model evaluation, and monitoring after release.
Strong ML foundations, including deep learning with PyTorch, regression, anomaly detection, and calibrated uncertainty.
Experience with MLOps, including reproducible training, dataset and model versioning, model registries, CI/CD, monitoring, and GPU-aware inference optimization; familiarity with agile and DevOps practices.
Experience rigorously evaluating AI systems by building test sets, defining metrics, and reporting system failures honestly.
Deep Python skills and strong software engineering knowledge, including data structures, design patterns, object-oriented design, and writing clean, tested production code.
Hands-on experience with AI-assisted development tools, including writing clear prompts, critically reviewing generated code, and converting it into maintainable production code.
Working understanding of software security, intellectual property, data privacy, and responsible AI in enterprise software.
Strong analytical and troubleshooting skills for complex software systems and ability to research and solve difficult technical problems independently.
Experience developing software on Windows with Visual Studio and Azure DevOps.
Experience owning AI systems in production after launch, including monitoring, diagnosing failures, and shipping updates.
Clear technical writing and ability to explain AI decisions to process engineers.

Nice To Haves

Strong programming skills in C++, C#, or CUDA.
Semiconductor process control experience, such as metrology, inspection, SPC, or yield analytics, or experience working in a fab.
Experience with scatterometry or OCD, ellipsometry, reflectometry, interferometry, or e-beam imaging.
Experience with tool-calling and MCP frameworks, multi-agent orchestration, vector and hybrid search, LLM fine-tuning, or on-premises LLM serving.
Experience with AI system security and IP protection, regulated release processes, or customer data that cannot leave the site.
Experience with physics-informed ML, surrogate modeling, physics-based modeling and numerical simulation, or Bayesian inverse methods such as MCMC or variational inference.
Parallel or high-performance computing experience.
Experience integrating AI into software development, such as AI-assisted code review, automated test creation, or requirements analysis.

Responsibilities

Define the AI strategy, reference architecture, and roadmap for metrology; make build-versus-buy decisions and align the roadmap with customer problems.
Write, test, and ship production code for prototypes, agent workflows, evaluation tools, and supporting systems.
Design agent workflows for recipe and model setup, qualification runs, tool matching, and root-cause triage for measurement drift.
Connect agents to simulators, solvers, and tool data so agents orchestrate work while physics-based tools perform computations.
Ground agents in fab knowledge, including manuals, recipes, service tickets, and historical measurement outcomes, and provide provenance for answers.
Design trustworthy systems with human-in-the-loop checkpoints, confidence and uncertainty, audit trails, and refusal when evidence is insufficient.
Deploy AI systems on-premises or in air-gapped environments, selecting local or hosted models according to latency, cost, and data-control constraints, and support customer change control.
Build and maintain evaluation harnesses, including golden task sets, tool-call correctness tests, recipe comparisons against the TMU budget, and regression tests for model or prompt changes.
Own relevant ML for measurement science, including surrogate models, parameter inference, tool calibration, calibrated uncertainty, and domain shift across tools, layers, and fabs.
Set technical standards, conduct design and code reviews, mentor engineers, and guide technical direction and architecture decisions.
Improve software quality through unit testing, automated CI/CD testing, refactoring, and static and dynamic analysis.
Establish responsible AI-assisted development practices for coding, debugging, documentation, and test generation, including human review, automated testing, security scanning, and requirements validation.
Identify gaps in team processes and toolchains and drive improvements.
Translate customer setup or yield problems into agent workflows and explain results to process engineers against reference techniques.
Monitor AI systems after launch, diagnose failures, and ship updates.