Data Scientist

About the Role

Context Labs is seeking an early-career Data Scientist to support the deployment of Context Labs’ Decarbonization as a Service™ platform, built on our Immutably™ Data Fabric technology. This role sits at the intersection of data science, engineering, and scientific computing. You will work with complex, real-world energy and emissions data and collaborate with application engineers, data engineers, and product teams to translate engineering methodologies and research ideas into robust, scalable analytical capabilities.

We do not expect you to arrive knowing every technology, emissions methodology, or aspect of the energy industry. We do expect strong quantitative reasoning, Python and SQL skills, and the curiosity and initiative to learn unfamiliar technical subjects and take ownership of challenging problems. This position reports to the Data Science Architect.

Key Responsibilities

• Work with domain experts to understand engineering and emissions methodologies, assumptions, and requirements and translate them into computational solutions.
• Develop, implement, validate, and document robust and reproducible emissions calculations and analytical methodologies.
• Explore complex customer datasets, understand their structure and meaning, identify data-quality issues, and investigate discrepancies.
• Implement scalable analytical workflows using Python, SQL, and PySpark, working with data engineers to move solutions into repeatable production workflows.
• Help generalize customer-specific calculations, research ideas, and analytical prototypes into reusable software and product capabilities.
• Apply statistical methods to validate results, quantify uncertainty, and understand the limitations of available data and methodologies.
• Work within an ontology- and knowledge-graph-based framework to connect data to the entities, relationships, and concepts they represent.
• Write maintainable, modular Python code and contribute through Git, code review, testing, and documentation.
• Apply machine learning methods, including regression, classification, time-series analysis, and anomaly detection, when appropriate to the problem.
• Collaborate across Data Science, Data Engineering, Application Engineering, Product, R&D, and Customer Experience teams.
• Anything else as may reasonably be required by the company.

Requirements & Tech Stack

• Relevant professional experience in data science, scientific computing, engineering analytics, or related quantitative work.
• Strong Python and SQL skills, including experience developing maintainable, modular code beyond exploratory notebooks and working with complex, real-world datasets.
• Strong quantitative and analytical problem-solving skills, including comfort reasoning about equations, assumptions, data relationships, and statistical results.
• Working knowledge of statistics, including distributions, descriptive statistics, regression, and statistical validation.
• Experience investigating messy or heterogeneous datasets, identifying data-quality issues, and developing defensible analytical approaches.
• Familiarity with collaborative software-development practices such as Git, code review, testing, and documentation.
• Strong initiative and demonstrated ability to learn unfamiliar technical subjects, ask effective questions, seek out relevant expertise, and progressively take ownership of new problems.
• Ability to communicate analytical approaches, assumptions, and results clearly to technical and non-technical colleagues.

Qualifications

• BS or MS degree in Engineering, Physics, Applied Mathematics, Data Science, or another related quantitative scientific or technical discipline.

Bonus Skills

• Experience working with energy, utilities, industrial, environmental, or emissions-related data, including greenhouse-gas or methane analytics.
• Familiarity with engineering or physical-system concepts such as mass and energy balances, thermodynamics, or process modeling.
• Experience with PySpark, Spark, Delta Lake, or other distributed data-processing technologies.
• Experience with uncertainty quantification, Monte Carlo methods or implementing scientific, engineering, or regulatory calculation methodologies in software.
• Knowledge of ontologies, knowledge graphs, or semantic modeling.