AI Scientist, Product Lifecycle Management (PLM)

Avathon • Pleasanton, CA

3d

About The Position

Avathon is hiring an AI Scientist to build models for Product Lifecycle Management (PLM) on its industrial AI platform. The role focuses on using manufacturer engineering data—including bills of materials (BOMs), part attributes, CAD metadata, drawings, specifications, and engineering change history—to support part similarity and substitution, engineering-change impact prediction, document and drawing information extraction, and engineering search. Models operate on a Computational Knowledge Graph linking parts with suppliers, orders, production, and field assets. The position is in Product Engineering and involves taking models from research through production in collaboration with the PLM engineering team.

Requirements

• PhD in Computer Science, Machine Learning, Mechanical Engineering, or a related field, or an MS with at least 5 years of relevant industry experience.
• Strong foundation in machine learning and depth in at least one of graph learning, NLP/LLMs, or computer vision on documents.
• Experience applying machine learning to engineering or manufacturing data such as BOMs, CAD, drawings, or part catalogs.
• Strong Python skills and experience with the standard ML stack, including PyTorch, Hugging Face, and graph libraries.
• Experience shipping models to production, beyond working in notebooks.

Nice To Haves

• Experience at a PLM or CAD vendor such as Siemens, PTC, Dassault Systèmes, Autodesk, or Oracle, or at an engineering-heavy manufacturer.
• Publications or patents in related areas.

Responsibilities

• Build part similarity, classification, and substitution models using part attributes, BOM structure, and CAD metadata.
• Build models to predict the downstream impact of engineering changes across BOMs, suppliers, and production.
• Extract structured data from drawings, specifications, and engineering documents using vision and language models.
• Apply graph learning to the Computational Knowledge Graph for link prediction, entity resolution, and change-impact analysis.
• Build retrieval and LLM-based tools that let engineers search parts, drawings, and change history using plain language.
• Use Normal Behavior Models to flag unusual change activity, such as spikes in engineering change request volume on a product line.
• Work with engineering to put models into production, including evaluation, monitoring, and clear explanations.
• Work with AI agents that help engineers and planners act on change-impact information.
• Clearly document methods and results for product teams, customers, and leadership.

Benefits

• Professional growth in a fast-scaling startup environment.
• Opportunity to work on AI-driven projects intended to create meaningful change across industries.

What This Job Offers

• Job Type: Full-time
• Education Level: Ph.D. or professional degree