LG Energy Solution Vertech (LGES Vertech) is seeking a Data Scientist to develop and deploy advanced machine learning solutions for Battery Energy Storage Systems (BESS) to address critical challenges in system performance, anomaly detection, diagnostics, and predictive maintenance.
Requirements
- 3-6 years of hands-on experience applying machine learning in signal processing, manufacturing, energy or other related industry.
- Demonstrated ability to independently develop and deploy custom machine learning algorithms, not just using off-the-shelf models.
- Proven expertise in anomaly detection, fault diagnostics, and system-level prognostics using time series and high-frequency data.
- Experience working with complex, noisy datasets from physical systems, with a strong emphasis on signal interpretation and pattern extraction.
- Strong Python development skills, including best practices in modular, scalable, and testable codebases.
- Deep understanding of both supervised and unsupervised learning methods; able to apply advanced models such as isolation forests, autoencoders, Bayesian inference, or graph-based methods.
- Familiarity with machine learning frameworks such as PyTorch, TensorFlow, or Scikit-learn.
Responsibilities
- Design and develop advanced machine learning solutions to detect anomalies, diagnose root causes, and forecast potential failures in Battery Energy Storage Systems (BESS).
- Take ownership of projects end-to-end from problem formulation and data exploration to model development, validation, and deployment in production environments.
- Build and maintain custom diagnostic and prognostic models that go beyond event detection to generate actionable insights for reliability, safety, and performance optimization.
- Collaborate closely with domain experts, data engineers, and DevOps to ensure models are integrated into scalable cloud-based pipelines.
- Lead research and prototyping of new methods, including unsupervised learning, statistical modeling, and signal processing techniques, to handle complex time-series and event data.
- Analyze large-scale, imperfect, and noisy datasets from deployed field systems to uncover hidden patterns, trends, and failure modes.
- Contribute to and maintain a robust, modular codebase with clear documentation and versioning practices, following software engineering best practices.
Other
- Bachelor’s or Master’s degree in Computer Science, Data Science, Engineering, or a related quantitative discipline.
- Must be legally authorized to work in the U.S. without employer sponsorship.
- M.S or Ph.D. in Computer Science, Engineering, Physics, or a related field.
- Familiarity with cloud platforms: AWS, Azure, GCP, Databricks, or Snowflake.
- Familiarity with MLOps tools for model deployment, monitoring, and lifecycle management.
