What we're loking for

Spectral Labs is looking for a Geometry Engineer to work alongside our core team, building the geometry and data pipelines that will power the next generation of CAD foundation models. You’ll work at the intersection of computational geometry, CAD kernel internals, and AI research, collaborating directly with our research team on decisions that span data representation and model architecture. This is a high-impact role that will shape the quality and capabilities of our models.

Responsibilities

• Design and build high-performance geometry pipelines that ingest CAD data across different file formats, extracting and converting B-rep geometry, feature trees, and parametric data into universal feature representations for ML consumption.
• Work directly inside or on top of CAD kernels to extract, manipulate, and reason about solid geometry programmatically.
• As the processed data representation evolves together with the model, collaborate with the research team on model architecture/design decisions.
• Build automated systems for CAD data extraction, encoding, reconstruction, and verification across the full pipeline.
• Depending on experience, lead our data collection & curation efforts
• Work closely with a small, elite team of researchers and engineers across domains.

Qualifications

• 3+ years of experience in relevant engineering field with experience in computational geometry, CAD data processing, and/or geometry kernel development. You’ve built real pipelines that operate on real CAD data.
• Direct experience working with or alongside at least one CAD or geometry kernel API: Parasolid, ACIS, or comparable. You understand kernel internals and computational geometry from first principles, including the underlying mathematics and algorithms, rather than just high-level API integration or CAD application usage.
• Strong working knowledge of B-rep geometry, NURBS curves/surfaces, and solid modeling fundamentals.
• Strong intuitive grasp of 3D geometry, demonstrated through background.
• Familiarity with CAD data interchange formats and the practical challenges of parsing and converting between them.
• Experience solving problems that stump others. Must love the process of solving hard problems.
• Proficiency in C/C++ and comfort working in complex codebases.

Strong Pluses

• Experience with feature tree extraction and parametric/history-based modeling internals.
• Exposure to computational geometry algorithms beyond what kernels provide already.