Agentic AI — PhD Intern (Autonomous AI Agent)

Keysight Technologies, Inc. • Calabasas, CA

2d

About The Position

Keysight’s AI team builds adaptive engineering intelligence systems that combine measurement, simulation, and machine learning. This internship focuses on reliable autonomous AI agents for multi-step engineering workflows. The intern will design, build, and evaluate an agentic workflow for a defined engineering process. The system will interpret incoming information, identify next steps, use approved tools, track progress, and incorporate feedback as work evolves.

The work emphasizes bounded, auditable, and recoverable actions so engineers can understand what the agent did and why, what remains open, and where approval is required. The intern will collaborate with AI researchers, software engineers, and engineering stakeholders. Learning outcomes include applying agentic AI to realistic engineering workflows; designing stateful systems with durable context, provenance, recovery, and human approval points; evaluating continuity, reliability, completion, and intervention; and gaining experience with tool integration, workflow automation, task-state management, and auditability.

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 evaluating non-deterministic systems, including benchmark design, held-out test sets, and automated scoring.
• A portfolio of agent or LLM systems the candidate has built, with code available for review and an account of how the systems were evaluated.
• Working knowledge of application state, task management, context handling, and tool integration.
• Sound judgment about autonomy, including when an agent should act, ask, or refuse.
• Clear communication with AI researchers and domain engineers.
• Familiarity with Git, modular software development, and reproducible experiment workflows.
• Comfort working with existing workflow, planning, document, and engineering tools rather than clean-room examples.
• Ability to design evaluations measuring task completion, continuity, reliability, and human intervention.
• Ability to clearly communicate state, assumptions, actions, limitations, and escalation points.
• 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 agent frameworks, MCP or comparable tool-integration protocols, and stateful application design.
• Background in workflow automation, task orchestration, enterprise software, or event-driven systems.
• Exposure to engineering or test and measurement workflows spanning multiple tools and handoffs.
• Experience with retrieval-augmented systems, structured context, knowledge graphs, or provenance tracking.
• Familiarity with C++ for integration with internal engineering tooling.

Responsibilities

• Build an autonomous agentic workflow that maintains task state and context across multiple steps and sessions.
• Develop tool integrations connecting the system to approved communication, planning, document, workflow, and engineering applications.
• Implement mechanisms for incorporating new information, updating task state, and resuming incomplete work.
• Develop state and provenance mechanisms for decisions, actions, outcomes, and feedback.
• Design guardrails for approval, permissions, bounded actions, failure recovery, and escalation.
• Assemble representative engineering workflows and measure completion rate, reliability, continuity, and human intervention against a suitable baseline.

Benefits

• Mentorship across agentic AI, software systems, and engineering workflows, with access to representative engineering use cases.
• Opportunity to complete a portfolio-defining applied agentic AI project 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