Onto Innovation
Lead AI Engineer — Semiconductor AI Innovation
Onto Innovation, Wilmington, Massachusetts, us, 01887
Overview
Lead AI Engineer — Semiconductor AI Innovation at Onto Innovation. Location: Wilmington, MA (On-site). Onto Innovation is a leader in process control, combining global scale with an expanded portfolio of leading-edge technologies across the semiconductor value chain to help customers solve yield, device performance, quality, and reliability issues. Responsibilities
Define the AI strategy and architecture for integrating machine learning into core engineering and manufacturing processes. Partner with tool, process, and applications engineers to map as-is processes and define a to-be AI/automation architecture and deliver measurable outcomes. Ship agentic assistants for use-cases. Stand up LLM + RAG + tool integrations (via MCP servers) that help engineers accelerate tool operation/setup/maintenance and explain trade-offs, grounded in internal docs, logs, and historical inspection outcomes. Lead projects across diverse areas: Predictive maintenance for tool health monitoring and failure detection. Computer vision for wafer defect detection, segmentation, and classification. LLM-based engineering assistants using RAG and MCP agents to make internal knowledge more accessible. Process optimization & yield improvement through data-driven insights and parameter tuning. Simulation and digital twins to model process behaviors and accelerate R&D. Build retrieval-augmented AI assistants to query internal knowledge bases, tools, and logs. Architect robust pipelines for data ingestion, labeling, storage, and retrieval across massive multi-modal datasets (images, telemetry, recipes, logs). Stand up scalable MLOps infrastructure: model registries, monitoring, evaluation, deployment, and governance. Hire, mentor, and manage a team of 3 engineers focused on LLM/Agents, CV/ML, and MLOps/Data. Work cross-functionally to integrate AI solutions into production environments safely and securely. Minimum Qualifications
5+ years applied ML/AI experience, with 3+ years in a technical leadership role. Hands-on expertise with at least two of the following domains: Large Language Models - RAG, fine-tuning, agent frameworks, prompt optimization. Predictive Modeling - tool failure prediction, anomaly detection, time-series analysis. Computer Vision - defect detection, segmentation, or SEM/optical imaging. Strong background in ML systems architecture and production deployment. Advanced Python proficiency: C++/CUDA familiarity is a plus. Experience with MLOps stacks: containers, CI/CD, Ray Serve/Triton, model registries (e.g., MLflow), and GPU optimization. Strong stakeholder collaboration skills and the ability to translate between engineering, operations, and leadership. Demonstrated success delivering AI-powered products into production. Nice-to-Haves
Familiarity with semiconductor manufacturing, inspection, or metrology. Understanding of fab interfaces and data connectivity (SECS/GEM, GEM300). Prior experience deploying digital twins or simulation-driven optimization. Knowledge of vector databases, retrieval pipelines, and hybrid search. Experience implementing safety, security, and IP protections for AI systems. Exposure to datasets or tools from KLA, ASML, Applied Materials, Onto, Nova, or similar inspection/metrology vendors. What Success Looks Like
90 days: Map high-value AI opportunities, propose architecture, and deliver a prioritized roadmap. 6 months: Deliver first production pilot (e.g., predictive tool health, RAG assistant, or wafer defect CV model) and hire first two engineers. 12 months: Multiple AI-powered systems integrated into engineering workflows, delivering measurable impact on yield, efficiency, and downtime. Our Tech Stack
LLMs & Agents: OpenAI, Anthropic, HuggingFace, MCP-based connectors, LangChain, LlamaIndex Predictive Models: PyTorch, TensorFlow, Scikit-learn, XGBoost, Time-series ML Computer Vision: PyTorch, OpenCV, Kornia, segmentation/detection architectures Data & Serving: Triton, Ray Serve, MLflow, Kubernetes, Kafka, vector DBs, GPU compute clusters Why Join Us
Build foundational AI infrastructure in one of the most data-rich industries in the world. Lead the team shaping the future of AI-assisted semiconductor engineering. Tackle multi-modal AI challenges at scale—from LLMs to predictive analytics to advanced vision systems. Collaborate with world-class engineers pushing the limits of nanometer-scale inspection and manufacturing. Equal Opportunity
Onto Innovation Inc. is an Equal Opportunity Employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, gender, sexual orientation, national origin, genetic information, age, disability, veteran status, or any other legally protected basis. For positions requiring access to technical data, Onto Innovation Inc., Inc. may have to obtain export licensing approval from the U.S. Department of Commerce - Bureau of Industry and Security and/or the U.S. Department of State - Directorate of Defense Trade Controls. As such, applicants for this position – except US Citizens, US Permanent Residents, and protected individuals as defined by 8 U.S.C. 1324b(a)(3) – may have to go through an export licensing review process.
#J-18808-Ljbffr
Lead AI Engineer — Semiconductor AI Innovation at Onto Innovation. Location: Wilmington, MA (On-site). Onto Innovation is a leader in process control, combining global scale with an expanded portfolio of leading-edge technologies across the semiconductor value chain to help customers solve yield, device performance, quality, and reliability issues. Responsibilities
Define the AI strategy and architecture for integrating machine learning into core engineering and manufacturing processes. Partner with tool, process, and applications engineers to map as-is processes and define a to-be AI/automation architecture and deliver measurable outcomes. Ship agentic assistants for use-cases. Stand up LLM + RAG + tool integrations (via MCP servers) that help engineers accelerate tool operation/setup/maintenance and explain trade-offs, grounded in internal docs, logs, and historical inspection outcomes. Lead projects across diverse areas: Predictive maintenance for tool health monitoring and failure detection. Computer vision for wafer defect detection, segmentation, and classification. LLM-based engineering assistants using RAG and MCP agents to make internal knowledge more accessible. Process optimization & yield improvement through data-driven insights and parameter tuning. Simulation and digital twins to model process behaviors and accelerate R&D. Build retrieval-augmented AI assistants to query internal knowledge bases, tools, and logs. Architect robust pipelines for data ingestion, labeling, storage, and retrieval across massive multi-modal datasets (images, telemetry, recipes, logs). Stand up scalable MLOps infrastructure: model registries, monitoring, evaluation, deployment, and governance. Hire, mentor, and manage a team of 3 engineers focused on LLM/Agents, CV/ML, and MLOps/Data. Work cross-functionally to integrate AI solutions into production environments safely and securely. Minimum Qualifications
5+ years applied ML/AI experience, with 3+ years in a technical leadership role. Hands-on expertise with at least two of the following domains: Large Language Models - RAG, fine-tuning, agent frameworks, prompt optimization. Predictive Modeling - tool failure prediction, anomaly detection, time-series analysis. Computer Vision - defect detection, segmentation, or SEM/optical imaging. Strong background in ML systems architecture and production deployment. Advanced Python proficiency: C++/CUDA familiarity is a plus. Experience with MLOps stacks: containers, CI/CD, Ray Serve/Triton, model registries (e.g., MLflow), and GPU optimization. Strong stakeholder collaboration skills and the ability to translate between engineering, operations, and leadership. Demonstrated success delivering AI-powered products into production. Nice-to-Haves
Familiarity with semiconductor manufacturing, inspection, or metrology. Understanding of fab interfaces and data connectivity (SECS/GEM, GEM300). Prior experience deploying digital twins or simulation-driven optimization. Knowledge of vector databases, retrieval pipelines, and hybrid search. Experience implementing safety, security, and IP protections for AI systems. Exposure to datasets or tools from KLA, ASML, Applied Materials, Onto, Nova, or similar inspection/metrology vendors. What Success Looks Like
90 days: Map high-value AI opportunities, propose architecture, and deliver a prioritized roadmap. 6 months: Deliver first production pilot (e.g., predictive tool health, RAG assistant, or wafer defect CV model) and hire first two engineers. 12 months: Multiple AI-powered systems integrated into engineering workflows, delivering measurable impact on yield, efficiency, and downtime. Our Tech Stack
LLMs & Agents: OpenAI, Anthropic, HuggingFace, MCP-based connectors, LangChain, LlamaIndex Predictive Models: PyTorch, TensorFlow, Scikit-learn, XGBoost, Time-series ML Computer Vision: PyTorch, OpenCV, Kornia, segmentation/detection architectures Data & Serving: Triton, Ray Serve, MLflow, Kubernetes, Kafka, vector DBs, GPU compute clusters Why Join Us
Build foundational AI infrastructure in one of the most data-rich industries in the world. Lead the team shaping the future of AI-assisted semiconductor engineering. Tackle multi-modal AI challenges at scale—from LLMs to predictive analytics to advanced vision systems. Collaborate with world-class engineers pushing the limits of nanometer-scale inspection and manufacturing. Equal Opportunity
Onto Innovation Inc. is an Equal Opportunity Employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, gender, sexual orientation, national origin, genetic information, age, disability, veteran status, or any other legally protected basis. For positions requiring access to technical data, Onto Innovation Inc., Inc. may have to obtain export licensing approval from the U.S. Department of Commerce - Bureau of Industry and Security and/or the U.S. Department of State - Directorate of Defense Trade Controls. As such, applicants for this position – except US Citizens, US Permanent Residents, and protected individuals as defined by 8 U.S.C. 1324b(a)(3) – may have to go through an export licensing review process.
#J-18808-Ljbffr