Senior R&D AI Software Development Engineer

Overview:

Keysight is at the forefront of technology innovation, delivering breakthroughs and trusted insights in electronic design, simulation, prototyping, test, manufacturing, and optimization. Our ~16,800 employees create world-class solutions in communications, 5G, automotive, energy, quantum, aerospace, defense, and semiconductor markets for customers in over 100 countries. Learn more about what we do.

Our award-winning culture embraces a bold vision of where technology can take us and a passion for tackling challenging problems with industry-first solutions. We believe that when people feel a sense of belonging, they can be more creative, innovative, and thrive at all points in their careers.

About the Team

You will join a high-performing Keysight R&D team developing next-generation Electronic Design Automation (EDA) workflow solutions for High-Speed Digital (HSD), signal integrity, power integrity, and adjacent simulation-driven engineering domains. The team is advancing how engineers interact with complex EDA tools by combining strong product APIs, engineering-domain knowledge, AI/ML methods, and agentic workflow automation.

Within the Agile development team, you will help design and implement production-quality AI agents, skills, MCP servers, and orchestration layers that allow engineers to safely automate, supervise, and accelerate design-analysis workflows across Keysight software environments.

Responsibilities:

As a Senior AI Software Development Engineer, you will develop agentic AI capabilities that connect large language models, EDA applications, simulation engines, product APIs, knowledge sources, and user workflows. Your work will enable supervised, goal-driven automation where AI agents can plan, invoke tools, reason over results, and assist with repeatable design-analysis tasks.

Build and maintain MCP-enabled agent infrastructure, including servers, clients, skills, tool schemas, orchestration services, guardrails, and evaluation frameworks.

Translate EDA workflow use cases into reliable AI-agent capabilities, such as simulation setup assistance, design diagnostics, optimization workflows, compliance-test setup, report generation, and guided automation.

Apply neural-network techniques where appropriate, including surrogate modeling, embeddings, vector search, model evaluation, physics-aware or data-driven models, and AI-based acceleration of expensive simulation workflows.

Develop production-quality backend services in Python and/or other modern languages with strong attention to reliability, observability, testing, maintainability, and secure deployment.

Qualifications:

Technical Qualifications

Strong software engineering skills in Python, with experience building production-grade services, libraries, automation tools, or developer-facing APIs.

Hands-on experience with AI-agent or copilot-style solutions using LLMs, tool calling/function calling, planner-executor patterns, retrieval-augmented generation, and agent orchestration frameworks.

Practical knowledge of Model Context Protocol (MCP), including server/client concepts, tools, resources, prompts, schema design, secure tool invocation, and local or remote deployment patterns.

Experience with AI/ML and neural-network concepts relevant to engineering workflows, such as deep learning, surrogate models, embeddings, vector databases, structured outputs, prompt engineering, and context management.

Strong grasp of modern software-development practices: Agile delivery, Git-based workflows, code review, CI/CD, automated testing, package management, security reviews, and documentation.

Preferred Qualifications

Experience with EDA, CAD, simulation, high-speed digital design, signal integrity, power integrity, RF/microwave design, photonics, or scientific/engineering software.

Experience with product APIs, desktop application automation, Python scripting inside engineering tools, or integration of AI agents with domain-specific software environments.

Familiarity with neural-network-based surrogate modeling for accelerating simulation, design-space exploration, optimization, or rapid what-if analysis.

Familiarity with LLM application frameworks, agent frameworks, vector databases, knowledge graphs, semantic search, workflow orchestration platforms, or cloud-based deployment environments.

Exposure to C++, C#, TypeScript, or JavaScript is beneficial when integrating AI services with engineering desktop applications or web-based workflow interfaces.

Soft Skills & Collaboration

Strong collaboration skills across multi-site and multi-cultural teams, including R&D, product management, application engineering, and customer-facing stakeholders.

Clear written and spoken English communication, with the ability to explain AI-agent architecture, neural-network trade-offs, and engineering workflow impact to both technical and management audiences.

Ability to guide development teams, mentor junior engineers, and drive pragmatic adoption of AI in production engineering software.