R&D Engineer

Keysight Technologies, Inc.•Calabasas, CA

About The Position

Keysight is a leader in electronic design, simulation, prototyping, test, manufacturing, and optimization, serving diverse markets like communications, automotive, energy, and aerospace with approximately 15,000 employees across over 100 countries. The company fosters an award-winning culture that values innovation and belonging. The Applied AI Autonomy Initiative is developing a next-generation agentic orchestration framework using LangGraph and reinforcement learning to enable AI agents to reason, adapt, and coordinate across complex engineering workflows. This framework aims to transform prompts and design intents into executable orchestration strategies that evolve autonomously through iterative simulation and validation. The ambition is to surpass human limits in exploring design spaces, optimizing engineering workflows, and evolving orchestration strategies at an unprecedented scale and speed, moving towards a continuous learning substrate where structured data, physics-informed features, and feedback signals refine model accuracy and generalization.

Requirements

PhD or 3+ years of experience in machine learning, applied data science, computational modeling, or related technical fields.
Strong foundation in computer science fundamentals (data structures, algorithms, and distributed systems) and their application to ML systems.
Proven experience developing neural or hybrid ML models for engineering, physics, or signal-processing domains.
Hands-on experience with data preprocessing, feature engineering, and pipeline automation (Python, SQL, or equivalent).
Proficiency in PyTorch, libtorch, or similar frameworks for model development and training.
Experience implementing XAI methods for scientific or engineering models.
Strong programming proficiency in Python, with experience in C++ integration for high-performance model components.
Experience using data management and analytics tools (e.g., pandas, NumPy, Apache Arrow, SQL).
Familiarity with experiment tracking and MLOps tools (e.g., MLflow, DVC, or equivalent).
Demonstrated ability to apply statistical analysis, uncertainty modeling, and visualization to engineering datasets.
Passion for building interpretable, data-driven models that explain — not just predict — engineering phenomena.

Nice To Haves

Background in scientific computing, simulation-driven modeling, or surrogate model development.
Familiarity with hybrid physical–statistical modeling techniques.
Experience with data fusion across multiple measurement or simulation sources.
Understanding of uncertainty quantification, sensitivity analysis, and confidence scoring in model evaluation.
Exposure to high-performance computing (HPC) or GPU-based model training environments.
Understanding of data base schema and SQL.

Responsibilities

Build model intelligence and feedback infrastructure for engineering models to generalize across varying design and measurement scenarios, learn from real and simulated data streams, provide explainable and traceable predictions, and continuously improve performance and robustness through data-driven refinement.
Design and train ML models that capture engineering behaviors and physics-based relationships, developing predictive and surrogate models using experimental, simulation, and sensor data.
Design feature representations and conditioning schemas that encode physical parameters, system constraints, and test configurations, implementing model pipelines capable of adapting to new devices, topologies, or domains with minimal retraining.
Collaborate with domain engineers to align ML model design with real-world measurement, calibration, and test semantics.
Build robust data systems that convert engineering data into model-ready intelligence, developing data ingestion, transformation, and validation pipelines for structured, semi-structured, and streaming data.
Implement feedback loops where new simulation and measurement results automatically trigger data updates and retraining, designing augmentation and normalization strategies to enhance data diversity, reduce bias, and improve model stability.
Ensure traceable data versioning and reproducibility, including detailed lineage and metadata tracking.
Make engineering models transparent, interpretable, and auditable by integrating Explainable AI (XAI) methods into model training and validation workflows.
Develop diagnostic analytics dashboards to interpret model performance, bias, drift, and physical consistency, and create data and model introspection tools for engineers to inspect feature influence on predictions.
Establish confidence scoring and anomaly detection frameworks for model validation and trust in production applications.
Expand machine learning models portfolio for engineering and simulation-driven applications.
Improve and maintain data pipelines for model ingestion, feature extraction, and structured conditioning.
Implement explainability and performance diagnostics to ensure models remain interpretable and auditable.
Collaborate with simulation, measurement, and data science teams to align ML architectures with engineering use cases.
Continuously refine and validate models using real-world data feedback from measurement systems or simulation loops.