17 days ago
Hsinchu, Taiwan or Taipei, TaiwanEntry Level / Mid Level / Senior / Staff+
Responsibilities
- Own the QAIRT SDK on Windows on Snapdragon across developer APIs, sample tools, runtime inference, and the Hexagon neural network backend.
- Investigate and resolve runtime failures, inference accuracy issues, performance regressions, and production deployment problems.
- Port and enable new features and operator support across SDK releases for Qualcomm hardware acceleration cores.
- Design for API stability, version negotiation, binary compatibility, and correctness across independently evolving SDK, driver, SoC, and Windows versions.
- Drive architecture and technical decisions with HTP, platform, hardware, and driver stakeholders.
- Contribute to compatibility, performance, and runtime-correctness testing and tooling infrastructure.
Requirements
- Bachelor’s degree in Computer Science, Electrical Engineering, Engineering, Information Systems, or a related field, or a master’s or PhD in a related field.
- At least 3 years of software engineering experience in systems software, SDK development, or a related discipline; the additional qualification section lists 4+ years with a bachelor’s, 3+ with a master’s, or 2+ with a PhD.
- Proficiency in C/C++ and Windows platform development.
- Experience with large-scale software projects emphasizing correctness, stability, and maintainability.
- Proficiency with Git and Gerrit or comparable version control and code review tools.
- Understanding of system architecture, software design, API design, versioning, and cross-component compatibility.
- Ability to communicate technical concepts clearly across distributed, cross-functional teams.
- Preferred experience includes 8+ years in semiconductor, systems software, or consumer devices; Windows diagnostics with WinDbg, Application Verifier, or dumpbin; AI inference SDKs, runtime libraries, or compiler backends; PyTorch or ONNX Runtime deployment; and performance optimization on heterogeneous CPU, DSP, and GPU hardware.
- Experience using AI coding assistants such as Claude Code, ChatGPT, Codex, or Gemini in development workflows is preferred.
- Expertise in at least one of Windows ecosystem development, performance profiling and optimization, AI and deep learning fundamentals, or low-level SDK and runtime development.
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.