2 days ago
Calabasas, CA, USAIntern
H1B sponsor
Responsibilities
- Build an autonomous agentic workflow that maintains task state and context across multiple steps and sessions.
- Develop tool integrations with communication, planning, document, workflow, and engineering applications.
- Implement mechanisms for updating task state, incorporating new information, and resuming incomplete work.
- Develop state and provenance mechanisms for decisions, actions, outcomes, and feedback.
- Design guardrails for approvals, permissions, bounded actions, failure recovery, and escalation.
- Evaluate task completion, reliability, continuity, and human intervention against a suitable baseline.
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 using tool and function calling, orchestration, and context management beyond prompt-level experimentation.
- Experience rigorously evaluating non-deterministic systems through benchmark design, held-out test sets, and automated scoring.
- A portfolio containing agent or LLM systems with accessible code and descriptions of their evaluation.
- Working knowledge of application state, task management, context handling, and tool integration.
- Good judgment regarding when agents should act, ask for approval, or refuse.
- Clear communication with AI researchers and domain engineers.
- Preferred experience shipping agent or LLM-based systems to real users.
- Preferred experience with agent frameworks, MCP or comparable tool-integration protocols, stateful application design, workflow automation, task orchestration, enterprise software, event-driven systems, retrieval-augmented systems, structured context, knowledge graphs, provenance tracking, or C++ integration.
Benefits
- Mentorship across agentic AI, software systems, and engineering workflows.
- Access to representative engineering use cases and a portfolio-defining applied agentic AI project.
- Opportunity to build an AI system that supports multi-step engineering tasks across multiple tools.
- Opportunity to learn rigorous measurement of reliability, recovery, and human intervention in non-deterministic systems.
- Candidates must be enrolled in an accredited college or university as of September 2027.
Categories
About Keysight
Keysight Technologies builds electronic test and measurement instruments and software used for design, validation, and manufacturing by engineers in communications, semiconductor, aerospace and defense, automotive, and data center markets. Its portfolio includes oscilloscopes, signal and network analyzers, RF/microwave test systems, and EDA and network test software, sold with services and support. Founded in 2014 as a spin-off from Agilent Technologies, Keysight is a public company (NYSE: KEYS) headquartered in Santa Rosa, California.