Data Scientist – Semiconductor Domain Expert

Seattle, WA, US

Job Description / Skills Required

NOTE: This is a fully remote position that is open to both the US and Canada


Tignis, who just announced a new round of Series A Funding, provides AI process control solutions for industrial systems that fuse deep physics understanding with the latest in AI solutions. Tignis has developed groundbreaking virtual metrology technology that takes high fidelity simulations (models based on partial differential equations) and generates machine learning surrogate models that are six orders of magnitude faster. This enables never-before-possible process control use cases. Tignis has also designed and built a novel analytics and automation language to give AI superpowers to process engineers. And of course, Tignis provides software solutions for AI process control (Run2Run or realtime, augmented or fully autonomous).


Tignis has proven its technology with big name customers in semiconductor manufacturing, and is looking to expand its market from that foundation.


The Role:


We are looking for a data scientist with a background in an applied engineering or science field (e.g. chemical engineering, materials science, physics, or chemistry), who has domain expertise in the semiconductor industry. Someone who has non-trivial experience applying machine learning and data science and also has experience working as a process engineer in the semiconductor industry or working with data from semiconductor process tools. You will work with a small team to bring together your domain knowledge and machine learning to help semiconductor industry customers turn sensor data into business value. You will both have the chance to contribute to the core software product and work directly with customers. This role is permanently remote and does not report to an office.




  • Work with customers on their engineering challenges and design analytical solutions that combine the best in engineering, simulation, and machine learning
  • Use statistics and data science to make decisions based on data
  • Create machine learning models that can be deployed to production for industrial and manufacturing plants
  • Work with internal software engineering teams to help design software libraries that accelerate reusable machine learning
  • Communicate results to broad range of external and internal constituents, from engineer to CEO
  • Stay up to date with the latest in machine learning developments
  • Collaborate across disciplines to deliver an amazing customer experience




  • MS or PhD (preferred) in Chemical Engineering, Materials Science, Applied Physics, or Applied Chemistry.
  • You are excited about the power of machine learning to advance research and technology in your field, and have significant experience applying machine learning methods, potentially as part of your graduate research.
  • You've written code to solve real problems in your research, your work or your life. You enjoy the process of creation through code.
  • You have excellent and demonstrable written and verbal communication skills including the ability to create and deliver effective presentations.
  • You have sincere empathy for the customer and a commitment to delving deep into the challenges they present or experience.
  • You have a keen attention to detail, ability to multitask, and can work well under pressure.
  • Your natural tendency is to be curious, positive, and creative.


Preferred (please include on Resume if you have any relevant experience):


  • You have experience working with semiconductor manufacturing processes or associated datasets, such as thin film deposition (CVD, PVD, ALD, etc), photolithography, etch, CMP, etc
  • You have work experience as a process engineer utilizing engineering statistics, such as DOE or SPC
  • You have experience and are comfortable creating high fidelity simulations of physical processes, such as finite element modeling and computational fluid dynamics.
  • You have research or work experience utilizing Reinforcement Learning