About the role#
This internship focuses on building and evaluating reliable autonomous AI agent systems for multi-step engineering workflows. You will design a system that maintains context across long-running tasks, uses approved tools, incorporates new information, and helps engineers complete work efficiently. A core requirement is ensuring the system's actions are bounded, auditable, and recoverable. You will work alongside AI researchers, software engineers, and engineering stakeholders to deliver a workflow that people can supervise and use in real-world scenarios.
What you'll do#
- Build an autonomous agentic workflow that maintains task state and context across multiple steps and sessions.
- Develop tool integrations connecting the system to communication, planning, document, workflow, and engineering applications.
- Implement mechanisms for incorporating new information, updating task state, and resuming incomplete work.
- Create 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 baseline.
What you'll need#
- Currently pursuing or recently completed a PhD in Machine Learning, Computer Science, Electrical or Electronic Engineering, Applied Mathematics, or a related technical field.
- Hands-on experience building LLM agents using tool and function calling, orchestration, and context management.
- Strong Python and software engineering skills, including modular code, version control, and reproducible pipelines.
- Experience evaluating non-deterministic systems, including benchmark design, held-out test sets, and automated scoring.
- A portfolio of agent or LLM systems with accessible code and an account of how they were evaluated.
- Sound judgment regarding when an agent should act, ask, or refuse.
- Clear communication skills for interacting with AI researchers and domain engineers.
- Familiarity with Git, modular software development, and reproducible experiment workflows.
- Must be enrolled in an accredited college or university as of September 2027.
- Preferred: Industry experience shipping agent or LLM-based systems, experience with agent frameworks (like MCP), background in workflow automation or event-driven systems, exposure to engineering or test and measurement workflows, and familiarity with C++.
Location & details#
- Location: Calabasas, California.
- Modality: On-site.
- Term: Rolling.
- Pay: $51-$56 per hour for PhD interns.
About Keysight Technologies
Keysight Technologies provides software-centric solutions for design and development engineering. The company serves customers in markets including aerospace, defense, automotive, energy, and semiconductors. Based in Santa Rosa, California, the firm operates globally with a workforce of approximately 15,000 employees. It holds over 2,000 patents and supports nearly 32,000 customers worldwide.
How to get in at Keysight Technologies
Securing an internship at Keysight Technologies often requires being among the first to submit an application, as early candidates are reviewed before the applicant pool grows. Intern Insider sends an instant alert the moment a role matching your target is published, helping you maintain that timing advantage. Reaching out to the right people is equally important, as direct contact with recruiters often improves your response rates. Intern Insider surfaces the specific recruiters behind company roles, allowing you to connect with them directly regarding the position or a potential referral.
