Lead Battery Data Scientist — Lithium-Sulfur ML & Analytics

Lyten; San Jose (CA); On-site; USD 141,000 - 212,000; Full time

Job summary

Lyten in San Jose, CA seeks a Staff Battery Data Scientist to turn cell, process, and quality data into actionable insights. You will collaborate with R&D, process engineering, quality, and manufacturing to deploy ML models and dashboards that predict performance and identify failure drivers.

The role emphasizes end-to-end data science from data collection to production deployment, using Databricks/Snowflake, LLMS for automation, and mentoring junior team members.

Qualifications

• 8+ years in data science or analytics with manufacturing data.
• Experience with battery or high-volume data.
• Strong Python/SQL with ML stack.

Responsibilities

• Identify failure drivers in cell, process, and quality data and prioritize next steps for engineering and operations.
• Lead lithium–sulfur analytics, including cell-to-cell variation, capacity fade, formation behavior, and early-life prediction of long-term performance.
• Clean and analyze high-volume time series data from cyclers, formation equipment, and manufacturing tools, linking with cell-level quality data to find root causes.
• Build, validate, and deploy ML models for performance prediction, anomaly detection, and process optimization; know when a simpler method is better.
• Design DOE, SPC, and statistical testing that give engineers actionable decisions and communicate findings, including uncertainty, to technical and executive audiences.
• Use AI and LLM tooling to automate recurring analyses and build a searchable knowledge base.

Skills

Python

SQL

Time-series analysis

ML/AI

Databricks

Snowflake

LLMs

GitHub

Education

PhD in data science

Tools

Databricks

Snowflake

GitHub

ETL/ELT pipelines

Spark

MLflow

Job description

Lyten in San Jose, CA seeks a Staff Battery Data Scientist to turn cell, process, and quality data into actionable insights. You will collaborate with R&D, process engineering, quality, and manufacturing to deploy ML models and dashboards that predict performance and identify failure drivers.

The role emphasizes end-to-end data science from data collection to production deployment, using Databricks/Snowflake, LLMS for automation, and mentoring junior team members.