Agentic AI — PhD Intern (Modeling Agent)

Keysight Technologies, Inc. • Calabasas, CA

2d

About The Position

Keysight’s AI team builds adaptive engineering intelligence systems combining measurement, simulation, and machine learning. This PhD internship focuses on the agentic layer that makes these systems usable by engineering teams. The intern will design, build, and evaluate an agentic flow that takes a new engineering use case and establishes a modeling and optimization workflow with minimal manual configuration. The agent will analyze available data, propose and validate a setup, connect to approved execution tools, and explain its choices and results to engineers.

A central requirement is that the agent’s output be auditable and reproducible. Engineers should be able to understand why a configuration was selected, correct it, and rerun it deterministically. The intern will build a benchmark of representative engineering use cases and assess how reliably the flow completes bounded tasks with appropriate human oversight. The internship offers mentorship across agentic AI, software systems, and engineering workflows, and an opportunity to deliver a workflow that can be understood, supervised, and used in a real engineering process.

Requirements

• Currently pursuing or recently completed a PhD in Machine Learning, Computer Science, Electrical or Electronic Engineering, Applied Mathematics, or a related technical field, with experience building and evaluating agent systems.
• Strong Python and software engineering skills, including modular code, version control, and reproducible pipelines.
• Hands-on experience building LLM agents, including tool and function calling, orchestration, and context management beyond prompt-level experimentation.
• Demonstrated rigor in evaluating non-deterministic systems, including benchmark design, held-out test sets, automated scoring, and careful interpretation of results.
• A portfolio of agent or LLM systems built by the candidate, with code and an explanation of how they were evaluated.
• Working knowledge of the machine learning workflow the agent must configure, including data preparation, model selection, training, and optimization.
• Sound judgment about autonomy: knowing where an agent should act, ask, or refuse.
• Clear communication with both AI researchers and domain engineers.
• Must be enrolled in an accredited college or university as of September 2027.

Nice To Haves

• Industry experience shipping agent or LLM-based systems to real users.
• Experience with multi-agent systems or agent frameworks, and with MCP or comparable tool-integration protocols.
• Background in optimization, design of experiments, or surrogate modeling.
• Exposure to RF, microwave, or electromagnetic engineering problems.
• Experience with retrieval-augmented systems or structured generation.
• Familiarity with C++ for integration with internal engineering tooling.

Responsibilities

• Build an agentic flow that configures data preparation, model training, and optimization for a new use case with minimal user input.
• Develop tool integrations connecting the agent to simulation, data, optimization, and analysis systems.
• Implement autonomous data analysis so the agent can characterize an unfamiliar dataset and choose an appropriate setup.
• Build explainability into the flow, including explanations of configuration choices, model dependencies, and confidence.
• Design guardrails such as validation before expensive runs, bounded actions, and compute budgets so failures are cheap and visible.
• Assemble a benchmark of representative engineering use cases with objective success criteria, and measure task-completion reliability and result quality against an expert-configured baseline.
• Apply agentic AI to realistic engineering modeling and optimization workflows while gaining practical experience evaluating non-deterministic systems.
• Collaborate across AI research, software engineering, RF design, and test and measurement domains.

Benefits

• Mentorship across agentic AI, software systems, and engineering workflows, with access to representative engineering use cases.
• A portfolio-defining project in applied agentic AI, evaluated on reliability and usefulness in representative engineering workflows.
• Opportunity to build an AI system that works across engineering tools and supports multi-step engineering tasks.
• Opportunity to learn rigorous measurement of longer-running, non-deterministic systems, including reliability, recovery, and human intervention.
• Opportunity to deliver an agentic workflow that people can understand, supervise, and use in a real engineering process.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: Ph.D. or professional degree