Senior AI Engineer (LLM, RAG, Multi-Agent Systems)

Quick Facts

• Role: Senior AI Engineer focusing on LLM, RAG, and multi-agent AI for engineering productivity

• Focus: Scalable AI solutions using generative AI and machine learning to unlock insights from complex wireless hardware data

Description

Transform engineering productivity and enable advanced hardware design through machine learning and generative AI. Build intelligent agents that automate repetitive tasks, analyze high-dimensional data to surface hidden trends, and leverage historical design intelligence to help engineers make faster, more accurate decisions.

Responsibilities

• Integrate state-of-the-art LLMs (via cloud-based APIs and secure on-premise deployments)

• Develop safe, efficient agent mechanisms to invoke APIs, query high-dimensional databases, and interact with internal engineering tools

• Architect and maintain RAG pipelines and oversee LLM fine-tuning for domain-specific engineering data

• Lead development of multi-agent architectures with complex orchestration, coordination, and persistent state management

• Move AI solutions from prototypes to robust, production-scale internal services for high-volume engineering requests

Requirements

• 7+ years of experience in AI/ML projects; proven record architecting and deploying production-scale generative AI solutions

• Master’s or PhD in Artificial Intelligence, Machine Learning, Computer Science, or related field

• Expert-level knowledge of multi-agent system design, including orchestration, coordination, and persistent state management

• Strong command of agent communication protocols (e.g., MCP, A2A) and distributed agentic workflow frameworks

• Expert software development skills with architectural design principles and scalable modular systems

• Proven ability to lead cross-functional architecture discussions and translate product goals into system designs

Benefits

• Opportunity to directly influence next-generation wireless hardware innovation used worldwide

• Work at the intersection of hardware, data, and AI, building scalable internal AI services for engineering teams