onnx-runtime jobs in San Diego

Design and develop the end-to-end compilation pipeline for Qualcomm AI Hub Workbench, enabling PyTorch and ONNX models to compile into deployable artifacts targeting LiteRT, ONNXRuntime, and QAIRT across Snapdragon SoCs. Own graph optimization, backend dispatch across CPU/GPU/NPU, model catalog validation, and automated CI/CD pipelines for on-device ML deployment.…See more Requires 4+ years of software/hardware/systems engineering experience and proficiency in Python and C++, with preferred expertise in ML compiler infrastructure, MLIR/ONNX/TVM, torch.export, and on-device frameworks.

Sr. Staff Software Engineer role designing and developing Multimedia, AI, and Gen AI SDKs/framework components for IoT products including drones, cameras, and media devices.…See more Requires 6+ years of software engineering experience with 3+ years in C, C++, Java, or Python, with strong preference for deep embedded systems expertise, real-time solutions, and AI/ML inference frameworks. Responsibilities include leading architecture and development of GStreamer-based SDKs, driving feature design across diverse product categories, and providing technical leadership on code quality and cross-functional collaboration.

Staff-level engineer responsible for designing and executing subsystem integration testing (SSIT) strategy for Qualcomm's Delegates ML inference framework. Develops and maintains Python/PyTest-based automated test suites integrated into CI pipelines, triages failures across the ML framework, QNN runtime, and HTP hardware stack, and owns the technical handoff criteria and traceability to downstream QA/SIT teams.…See more Leverages AI-assisted tooling (Claude Code, GitHub Copilot) to accelerate test generation and failure analysis. Mentors junior engineers and sets team standards for test coverage, debugging discipline, and documentation.

Staff Machine Learning Engineer role focused on designing and maintaining Qualcomm AI Hub's end-to-end ML compilation pipeline, from PyTorch and ONNX model ingestion through graph optimization to deployable artifacts on Snapdragon SoCs. Responsibilities span compiler infrastructure (graph transformation, op validation, backend dispatch across CPU/GPU/NPU), model catalog automation and CI/CD, and developer tooling for profiling and debugging.…See more Requires 4+ years of software/systems engineering experience (or 3+ with a master's, or 2+ with a PhD), with preferred expertise in ML compiler concepts, ONNX/PyTorch export workflows, and on-device deployment frameworks.

Staff-level software engineer responsible for subsystem integration testing (SSIT) of ML inference delegates on Qualcomm Snapdragon SoCs. Develops and maintains automated Python/PyTest test suites integrated into CI/CD pipelines, validates on-device behavior using hardware-in-the-loop infrastructure, and triages failures across the ML framework → QNN runtime → HTP hardware stack.…See more Acts as technical liaison between development and downstream QA/SIT teams, defining handoff criteria and owning test coverage strategy for the Delegates portfolio. Mentors junior engineers and sets team standards for test architecture, coverage discipline, and defect triage.

Staff-level CI/CD engineer responsible for building and maintaining hermetic, reproducible CI pipelines for ONNX Runtime, ExecuTorch, and LiteRT delegates across Linux, Windows (ARM64/x86), and Android. Owns end-to-end release engineering—versioning, artifact packaging (wheels, shared libraries, AARs), signed distribution, and automated quality gates—while integrating AI-assisted tooling (Claude, Copilot, Codex) into developer workflows.…See more Builds test automation frameworks for functional, performance, and regression testing at scale on Snapdragon SoC hardware, and drives cross-platform CI/build infrastructure alignment across a distributed global team.

Staff/Sr. Staff Software Engineer role focused on AI inference optimization on Snapdragon platforms, including model optimization, quantization, graph transformations, and runtime execution for LLMs, LVMs, and LMMs.…See more You will design and implement graph lowering and optimization techniques within ONNX Runtime, ExecuTorch, and Qualcomm AI Stack SDK, working across ML algorithms, inference systems, and hardware integration. The role requires 6–8+ years of software development experience, 3+ years in AI/ML inference or model optimization, deep expertise in Python and C/C++, PyTorch/ONNX, and transformer architectures. You will mentor junior engineers, drive features end-to-end, and collaborate across ML Research, hardware, product, and QA teams.

Design and develop embedded and cloud edge software applications focused on AI/GenAI, multimedia, and computer vision SDKs and frameworks for IoT products including drones, cameras, and AI boxes. Collaborate with systems, hardware, and architecture teams to build high-performance, real-time embedded software solutions.…See more Lead GenAI LLM/VLM inference workflows, multi-stream AI pipelines, and multimedia frameworks across Android, Linux, and embedded systems. Requires 2+ years of software engineering experience with C/C++, Python, or Java, plus preferred expertise in PyTorch, TensorFlow, ONNX Runtime, LangChain, LlamaIndex, Android architecture, Linux system programming, and graphics/GPU pipelines.

Staff-level embedded software engineer responsible for designing and developing AI, GenAI, and multimedia SDKs/frameworks for IoT edge devices (drones, cameras, AI boxes, appliances). The role requires architecting high-performance inference pipelines, multi-stream AI processing, and GStreamer-based plugins for Qualcomm hardware platforms.…See more Must have 5+ years of C/C++ experience in embedded systems, strong knowledge of AI inference frameworks (PyTorch, TensorFlow, ONNX Runtime, LiteRT), GenAI orchestration tools (LangChain, LlamaIndex), and multimedia/HAL integration across Android, Tizen, and Linux. Ownership spans architecture, design, implementation, and deployment of production-quality SDK components.

As a Senior Software Engineer focused on AI Tools, you will reauthor and optimize generative AI models (LLMs like Llama, Phi, Qwen, and multimodal models) for efficient execution on Qualcomm's on-device hardware. You'll translate hardware constraints into model-level transformations that preserve accuracy while enabling edge deployment, integrate inference acceleration techniques, and collaborate with compiler and quantization teams to move research prototypes into production.…See more The role requires deep implementation-level knowledge of generative AI architectures, strong Python proficiency in large typed codebases, and hands-on experience optimizing inference for resource-constrained environments.

Own CI, build, and release infrastructure for AI software products (ONNX Runtime, ExecuTorch, TFLite/LiteRT delegates) across Linux, Windows, and Android. Design and evolve multi-platform CI pipelines, implement HIL and on-device automated testing for Snapdragon SoC validation, and drive end-to-end release pipelines with versioning, artifact packaging, and distribution.…See more Define automated quality gates including regression benchmarks and performance thresholds. Requires 8+ years of software/DevOps/release engineering experience (or 6+ with a Master's), expert Python and Bash scripting, deep CI/CD platform expertise (Jenkins, GitLab CI, GitHub Actions, TeamCity), and hands-on experience integrating AI coding agents into workflows.

Qualcomm seeks an experienced Staff Product Manager to define and drive the Linux platform roadmap across Snapdragon-based AI PCs, Edge AI systems, and enterprise computing solutions. The role spans product strategy, Linux distribution enablement, upstream kernel and driver strategy, and AI developer platform support.…See more You will gather customer and ecosystem requirements, create product roadmaps, collaborate with OEMs, ISVs, Linux distribution partners, and open-source communities to deliver optimized Linux experiences on Snapdragon platforms. Success requires translating market needs into platform requirements, managing cross-functional alignment across hardware, firmware, kernel, and AI software layers.