PhD AI Agent Intern - Autonomous Workflow Builder

Anite; Calabasas (CA); On-site; USD 51,000 - 56,000; Full time

Benefits offered by this job

Mentorship across agentic AI

Portfolio-defining project

Access to engineering use cases

Job summary

Keysight's AI team is developing autonomous AI agent systems for multi-step engineering workflows. You will design, build, and evaluate an agentic workflow that interprets information, chooses next steps, uses approved tools, tracks progress, and remains auditable.

Expect collaboration with researchers, software engineers, and engineering stakeholders. The role emphasizes stateful design, provenance, and recovery, with evaluations of reliability, completion rate, and human intervention.

Qualifications

• PhD in Machine Learning, Computer Science, Electrical or Electronic Engineering, Applied Mathematics, or related field, with experience building and evaluating agent systems.
• Strong Python and software engineering: modular code, version control, reproducible pipelines.
• Hands-on experience building LLM agents - tool and function calling, orchestration, context management.
• Rigorous evaluation of non-deterministic systems: benchmark design, held-out test sets, automated scoring.
• A portfolio of agent or LLM systems with evaluative details.
• Knowledge of application state, task management, context handling, and tool integration.
• Judgment on autonomy: when to act, ask, or refuse.
• Clear communication to AI researchers and domain engineers.

Responsibilities

• Build an autonomous agentic workflow that maintains task state and context across steps and sessions.
• Develop tool integrations connecting the system to approved 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, and intervention against a baseline.

Skills

Python

LLM Agents

Agent Systems

Education

PhD in ML/CS/EE

Tools

Git

MCP

Job description

Keysight's AI team is developing autonomous AI agent systems for multi-step engineering workflows. You will design, build, and evaluate an agentic workflow that interprets information, chooses next steps, uses approved tools, tracks progress, and remains auditable.

Expect collaboration with researchers, software engineers, and engineering stakeholders. The role emphasizes stateful design, provenance, and recovery, with evaluations of reliability, completion rate, and human intervention.