Senior Architect Agentic Orchestration Frameworks

Keysight•Hidden Hills, CA

About The Position

Keysight is at the forefront of technology innovation, delivering breakthroughs and trusted insights in electronic design, simulation, prototyping, test, manufacturing, and optimization. Our ~15,000 employees create world-class solutions in communications, 5G, automotive, energy, quantum, aerospace, defense, and semiconductor markets for customers in over 100 countries. Learn more about what we do. Our award-winning culture embraces a bold vision of where technology can take us and a passion for tackling challenging problems with industry-first solutions. We believe that when people feel a sense of belonging, they can be more creative, innovative, and thrive at all points in their careers. Keysight's Applied AI Autonomy Initiative is developing a next-generation agentic orchestration framework that enables AI agents to reason, adapt, and coordinate across complex engineering workflows. Built on LangGraph and reinforcement-inspired feedback mechanisms , this framework transforms prompts and design intents into executable orchestration strategies that evolve autonomously through iterative simulation and validation loops. Our ambition is not merely to replicate human reasoning, but to push past human limits - enabling agentic systems to explore design spaces, optimize engineering workflows, and evolve orchestration strategies at a scale and speed no human could achieve. The goal is to create the foundational runtime for adaptive, multi-agent reasoning at scale , where AI systems not only execute tasks but collaborate, refine, and self-improve across engineering domains. This role sits at the intersection of machine learning, data engineering, and scientific modeling . You will build the model intelligence and feedback infrastructure that allows engineering models to: Generalize across varying design and measurement scenarios Learn from real and simulated data streams Provide explainable and traceable predictions Continuously improve performance and robustness through data-driven refinement The ideal candidate has a strong foundation in applied machine learning , scientific data analysis , and model interpretability , designing adaptive data systems where engineering models evolve intelligently over time. A defining opportunity to build the machine learning foundation that powers Keysight's next generation of engineering and simulation intelligence. The chance to design adaptive, explainable models that learn from complex measurement, simulation, and telemetry data — capturing real-world system behavior with scientific rigor. Direct impact on the architecture and evolution of scientific ML systems , shaping how engineering decisions are modeled, predicted, optimized, and explained. Deep collaboration with leading experts across simulation, AI, modeling, and measurement science , translating rich engineering data into transparent, high-assurance intelligence . A role where your work directly accelerates Keysight's shift toward self-improving engineering models and continuous learning pipelines .

Requirements

PhD or 5+ 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

Engineering Model Creation & Neural Conditioning Goal: Design and train ML models that capture engineering behaviors and physics-based relationships.
Develop 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.
Implement 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.
Data Intelligence, Feedback & Augmentation Goal: Build robust data systems that convert engineering data into model-ready intelligence.
Develop 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.
Design 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.
Explainable AI & Diagnostic Analytics Goal: Make engineering models transparent, interpretable, and auditable.
Integrate Explainable AI (XAI) methods (e.g., SHAP, LIME, attention visualization, or gradient attribution) into model training and validation workflows.
Develop diagnostic analytics dashboards to interpret model performance, bias, drift, and physical consistency.
Create data and model introspection tools that allow engineers to inspect how features influence 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.