Battery Data Scientist - Chemix, Inc.

Chemix is seeking a highly-motivated data scientist to develop and expand our AI platform for battery materials discovery. Our AI platform is the core of Chemix. Though data is first and foremost in any application of AI, it is typically very scarce in materials development. We've designed our R&D operation to generate large, high-quality battery materials datasets. As a data scientist at Chemix, your mission is to help develop machine learning models, perform statistical analyses, and ultimately design and implement the pipelines that turn our data into actionable results. You'll make a fundamental contribution to developing the batteries that will power the electrification revolution in transportation and beyond.

As an early employee at a fast-moving startup, we expect you to quickly and creatively solve all kinds of technical problems, including those beyond your core expertise. An ideal candidate is able to learn quickly, is eager to stretch their knowledge of the ML and data software stack, takes pride in the quality of their work, and wants to make a real impact in energy storage technologies for electric transportation.

Responsibilities:

• Develop machine learning and data pipelines for a wide variety of applications and types of battery data
• Discover and introduce new ML models, statistical methods, software frameworks, and libraries
• Contribute code to Chemix's internal codebase (Python)
• Interface with our machine learning scientists, battery engineers, and customers
• Implement best practices for code development and ML-ops, experiment tracking, etc
• Inform the optimization of the R&D process that generates our data

Requirements

• Bachelor's degree in computer science, or the physical, chemical, or biological sciences or engineering, combined with 3+ years of work experience in data science for the physical sciences
• Fluency in a variety of data science and statistics concepts
• Extensive experience with the python data science stack: pandas, numpy, sklearn, plotly, scipy
• Experience with the fundamentals of data science and software ops: git, testing, CI/CD
• Clear communication and good people skills
• Strong organization and ability to manage parallel projects

Nice to have:

• Experience with workflow orchestration tools, e.g. Airflow, Prefect, Luigi, and scaling tools such as Dask
• Experience with various modern neural network architectures such as transformers, GCNN, etc
• Experience with physics-based modeling of batteries (e.g. DFN model) and/or chemistry (DFT, MD, QC, etc)
• Experience with cloud web services (AWS, Google Cloud, Azure, etc.), Docker, Kubernetes
• Familiarity with experimental chemistry/materials science

Benefits

• Stock Option Plan
• Health Care Plan (Medical, Dental & Vision)
• Retirement Plan (401k)
• Paid Time Off (Vacation, Sick & Public Holidays)
• Family Leave (Maternity, Paternity)