Senior Data Scientist – Hardware Systems

What You Will Be Doing:

You will be responsible for developing the data and knowledge foundation that enables engineers to understand, operate, and improve Helion’s fusion systems. In this role, you will partner closely with engineers, scientists, and operators to transform complex experimental and operational data (including machine telemetry, experimental results, and engineering workflows) into structured datasets, knowledge systems, and AI-enabled tools that support analysis and decision-making. You will combine data science, knowledge modeling, and applied AI techniques to make fragmented, rapidly evolving information accessible and actionable at scale. This is an onsite role that reports directly to our R&D Manager at our Everett, WA office.

You Will:

• Analyze real-time and historical system data to provide control room operators with actionable insights, improve operational decision-making, and accelerate root-cause and performance analysis

• Develop data schemas, ontologies, and metadata frameworks to organize and standardize complex technical information

• Prototype decision-support tools for anomaly detection, experiment comparison, and operational reporting

• Define metrics and evaluation frameworks to ensure effectiveness, reliability, and business impact of statistical models and AI solutions

• Collaborate with the enterprise software engineering team to build and evaluate AI-powered workflows, including retrieval, summarization, and anomaly analysis systems using operational data

• Partner across Software Engineering and Data Science teams to evolve and maintain data pipelines that transform and integrate diverse data sources into analytics-ready datasets

Required Skills:

• 7+ years of experience applying statistics, data science, and quantitative methods to complex hardware, physics, or engineering data

• Experience analyzing operational, experimental, and time-series data to identify trends, diagnose hardware behavior, uncover anomalies, and inform engineering decisions is preferred

• Ability to translate ambiguous problems into practical, scalable solutions and partner effectively with engineers and scientists

• Proficiency in Python and modern data science tooling, with experience building data pipelines, analytics infrastructure, or production data systems

• Experience developing structured representations of information, including data models, schemas, metadata frameworks, or ontologies

• Familiarity with LLM APIs and applied AI techniques such as RAG, embeddings, semantic search, and AI-powered workflow automation

• Medical, Dental, and Vision plans for employees and their families

• 10 Paid holidays, plus company-wide winter break

• Up to 5% employer 401(k) match

• Annual wellness stipend