Staff Engineer – Robust AI Infrastructure
Qualcomm
- Location
- Shanghai, China
- Work model
- On-Site
- Level
- Staff
- H-1B history
- 22 approvals (FY2023)
- Posted
- Sep 1, 2026
Skills
About this role
Company: Qualcomm China Job Area: Engineering Group, Engineering Group > Software Test Engineering General Summary: We are seeking a highly motivated Staff Engineer to drive next-generation GenAI platform development and robust AI infrastructure for the automotive software engineering team. This role focuses on leveraging GenAI frameworks and APIs to build scalable AI-powered tools, intelligent agentic workflows, and engineering assistants that accelerate development velocity, improve product quality, and enhance engineering efficiency. The ideal candidate combines strong software engineering fundamentals with deep hands-on experience in GenAI application development and AI system integration.
Key Responsibilities
1. GenAI-Based Application & Tool Development • Leverage GenAI frameworks and APIs to design and develop AI-powered engineering tools and intelligent assistants for the automotive team. • Build and extend GenAI-powered multi-agent applications that support coding productivity, knowledge assistance, issue triage, and engineering task orchestration. • Develop agentic workflows using LangChain/LangGraph and Model Context Protocol (MCP) services to interface AI tools with internal systems (Jira, Confluence, Gerrit, Orbit, Axiom). • Integrate AI solutions with engineering systems such as source repositories, CI/CD toolchains, and internal platforms to deliver end-to-end productivity gains. • Rapidly prototype and evaluate emerging GenAI capabilities and deploy proof-of-concept solutions for high-impact engineering use cases. 2. Robust AI Infrastructure & Platform Development • Design and build scalable, reliable AI infrastructure that supports GenAI application development, deployment, and operation at team scale. • Develop and maintain RAG (Retrieval-Augmented Generation) pipelines, vector databases, and knowledge retrieval systems to power intelligent search and Q&A; applications. • Architect robust backend services and APIs that expose GenAI capabilities to engineering tools and agentic systems. • Ensure high availability, observability, and maintainability of AI platform components including model serving, prompt management, and inference pipelines. • Contribute to platform security, data privacy, and responsible AI practices in all developed systems. 3. AI System Advancement & Innovation • Drive practical integration of GenAI capabilities into engineering workflows to accelerate productivity and solution scalability. • Develop and optimize multi-agent architectures to improve engineering workflow orchestration and task automation. • Build intelligent dashboards and smart reporting tools that surface engineering insights through AI-driven analytics. • Collaborate with cross-functional teams to identify high-impact use cases and deliver innovative AI-powered solutions. • Champion AI best practices, contribute to internal knowledge sharing, and mentor teammates on GenAI platform development. Required Qualifications • Bachelor's or Master's degree in Computer Science, Electrical Engineering, Software Engineering, or related field. • 6+ years of experience in software engineering, with focus on AI/ML systems, platform development, or related technical domains. • Strong programming skills in Python, and familiarity with C/C++ or similar languages. • Hands-on experience with LLM integration, GenAI application development, and AI platform architecture. • Strong problem-solving skills with the ability to design and implement practical, production-grade engineering solutions. Preferred Qualifications • Experience with GenAI frameworks and APIs (e.g., LangChain, LangGraph, OpenAI API, or equivalent internal platforms). • Experience with Model Context Protocol (MCP) services and multi-agent system design. • Familiarity with RAG systems, vector databases (e.g., FAISS, Chroma), and knowledge retrieval pipelines. • Experience integrating internal or third-party tools with