Machine Learning Engineer 2

Role Overview

Keysight is at the forefront of technology innovation, delivering breakthroughs and trusted insights in electronic design, simulation, prototyping, test, manufacturing, and optimization. We are looking for a Machine Learning Engineer 2 to design, build, and maintain LLM-based agent workflows and advanced RAG pipelines.

Responsibilities

• Design, build, and maintain LLM-based agent workflows, including multi-step reasoning, tool/function calling, and human-in-the-loop approval steps.
• Evaluate and tune LLM usage across multiple providers and model tiers to balance accuracy, latency, and cost.
• Build and improve retrieval-augmented generation (RAG) pipelines: document processing, chunking, embeddings, and vector search.
• Develop and refine knowledge and memory systems for domain-specific technical content.
• Design prompts, structured tool schemas, and evaluation frameworks.
• Add observability for LLM and agent behavior via tracing and quality metrics.
• Collaborate with backend engineers to integrate ML components into a production Python service.
• Run structured experiments on models, prompts, and retrieval strategies.
• Participate in code review, automated testing, and production debugging.

Requirements

• Master's degree in Computer Science, Machine Learning, Electrical Engineering, or a related field.
• 2–4+ years of experience building production ML, NLP, or LLM-powered systems.
• Strong Python skills, including experience with asynchronous programming and typed data modeling.
• Hands-on experience with LLM application development: prompt engineering, tool/function calling, and structured output.
• Familiarity with Vector Databases and embedding-based retrieval.
• Understanding of agent orchestration concepts.
• Working knowledge of relational databases and caching layers.

Skills

• Python
• LLM
• RAG
• Vector Databases
• NLP