Cana is a consumer electronics company based in the SF Bay Area. We are a team of scientists, engineers, product managers and designers building products that redefine the future of food and beverage. Our first product will greatly reduce the environmental impact of beverages by changing how the world's most popular drinks are created, distributed and consumed. We are not building an incremental improvement over existing products, but rather completely reimagining how food is made to bring forward a better and more sustainable future.
If you are excited by the idea of working with a passionate team solving big challenges by bringing together the best of hardware, software and chemistry innovation, we want to hear from you!
Cana is committed to creating a workplace where you feel valued and can do your best work. We welcome candidates with backgrounds that are traditionally underrepresented in tech and hope you apply, even if the role below does not exactly describe you.
Senior Data Scientist
As a Senior Data Scientist, you’ll be a key stakeholder in championing the development and use of data science tools in flavor chemistry and food design. Your excitement in working with a small team, experience collaborating with cross-functional teams, and ability to work with scientific data generated in the lab will be instrumental in setting the foundations for data science at Cana. We’re building a category-defining experience that stands to make a huge positive environmental impact—that takes hard work, empathy, and a whole lot of teamwork.
About the role:
- Play a key role in Design, implement, and manage efficient ETL pipelines that enforce data quality and consistency standards in order to enable rapid downstream analyses and decision-making
- Work with chemists, engineers, and data scientists to implement a rapid design-create-test cycle for complex ingredients guided by and machine learning and efficient design of experiments
- Build models, algorithms, simulations, and performance evaluation by writing highly optimized, deployable code to solve problems, including outlier detection, multi-objective optimization, and multivariate (multi-response) classification and regression
- Develop machine learning approaches that learn consumer preferences in flavor/beverages and guide automated formulation designs
- Experience developing data science tools to be used by others (including scientists who are not experts in data science)
- Strong foundation in statistics and machine learning including in high-dimensional modeling problems as demonstrated by publications, presentations, or previous work experience
- Proficiency in python and SQL for data science and ETL pipelines
- Proficiency in bringing structure to ambiguous problems and deriving actionable insights from multiple information sources
- Strong attention to detail, excellent organizational and communication skills, and the ability to work efficiently in a fast-paced dynamic environment
- 5+ years experience as a data scientist working in an agile development environment
- 2+ years experience working with scientific data collected in the lab
- Demonstrated experience with designing, implementing, and managing ETL data pipeline
- Proficiency in Python, the PyData stack (e.g., numpy, pandas,..), and machine learning packages (e.g., scikit-learn, XGBoost, TensorFlow, ..)
- Strong coding, peer-review, and documentation practices, including using frameworks for testing your code (e.g., pytest), version control (e.g., GitHub) and virtual environment management (e.g., pipenv)
- Demonstrated deep understanding of the fundamentals of probability, statistics, and machine learning in order to solve complex problems in optimization, supervised and unsupervised learning, and design of experiments
- Experience with visual analytics and data storytelling/dashboarding using Tableau or other tools
- Graduate degree in a STEM field
- Experience with Python-based data dashboarding tools and frameworks (e.g., Streamlit, Dash, Voila, or Flask)
- Experience with AWS cloud resources (S3, EC2, SageMaker), and preferably with Docker
- Experience with cheminformatics toolkits (e.g., ChemDraw, RDKit, Schrödinger, etc.)
- Experience with machine learning techniques including Transformers, CNNs, RNNs to solve NLP tasks
Diversity at Cana:
- Cana is committed to building an inclusive workplace and diverse teams. We welcome interest from individuals of all backgrounds and levels of experience who share our mission.
Cana offers highly competitive salaries and benefits, including medical and dental insurance, paid time off, and 401(k)
Legal authorization to work in the U.S. is required. We are not able to sponsor individuals for employment visas for this job. In compliance with federal law, all persons hired will be required to verify identity and eligibility to work in the United States and to complete the required employment eligibility verification form upon hire. This position is based in our Emeryville, CA location - there is no relocation assistance offered at this time.