Engineer / Senior Engineer – AI Software Tools (Onsite)

Qualcomm•San Diego, CA

1d•Onsite

About The Position

As a leading technology innovator, Qualcomm pushes the boundaries of what’s possible to enable next-generation experiences and drive digital transformation, creating a smarter, connected future for all. As an Engineer / Senior Engineer in the Qualcomm AI Stack SDK Software team, you will contribute to the design, development, and delivery of AI/ML software solutions for on-device and edge AI inference on Snapdragon platforms. This role focuses on software implementation, optimization, and validation for modern AI architectures, with exposure to model optimization, quantization, graph transformations, and runtime execution. You will work at the intersection of machine learning, inference optimization, graph lowering, and systems software, contributing to the Qualcomm AI Stack SDK (QAIRT) and associated tools, including delegate support for ONNX Runtime, ExecuTorch, and TFLite/LiteRT frameworks. You will collaborate closely with senior engineers and cross-functional teams such as ML Research, AI accelerator HW/SW teams, Product Management, Program Management, and QA to help bring features from concept to production. This role emphasizes strong software fundamentals, hands-on development, and collaboration, with opportunities to grow technical ownership and responsibility over time.

Requirements

Bachelor’s degree in computer science, computer engineering, or a related field.
Engineer: Projects or Internships experience (Entry level) or 1+ years of experience in software development OR Senior Engineer: 2+ years of experience in software design, development, and delivery
Proficiency in Python and/or C & C++ for production software development.
Strong understanding of software engineering fundamentals, including data structures, algorithms, debugging, and testing.
Foundational understanding of AI/ML concepts, including deep learning and inference pipelines.
Ability to collaborate effectively within a team and communicate technical concepts clearly.
Good coding skills in Python or C/C++

Nice To Haves

Master’s degree in computer science, computer engineering, or electrical engineering.
1+ years of experience building embedded software applications.
Exposure to AI/ML inference or model optimization workflows.
Familiarity with graph-based ML representations and tooling (e.g., ONNX, TorchScript, MLIR).
Basic understanding of quantization techniques (e.g., PTQ, QAT) and performance tuning.
Experience or coursework involving transformer-based models, LLMs, or vision models.
Experience developing on Linux-based environments; exposure to Android or RTOS (e.g., QNX) is a plus.
Familiarity with git-based SCM, CMake-based builds, and agile development practices.

Responsibilities

Implement, optimize, and validate AI software features for inference on Snapdragon platforms.
Contribute to graph transformations, graph lowering, and runtime optimizations within AI runtimes such as ONNX Runtime, ExecuTorch, and Qualcomm AI Stack SDK.
Assist in applying quantization and performance optimization techniques to improve latency, throughput, memory usage, and power efficiency.
Work with modern AI models and algorithms, including transformers, and gain exposure to Generative AI inference concepts such as attention mechanisms, MoE, and LoRA.
Collaborate with ML Research and platform teams to prototype, validate, and integrate new ideas into SDK features.
Debug software issues across model, runtime, OS, and hardware layers, perform root-cause analysis, and contribute fixes.
Develop and maintain high-quality, well-documented code within the Qualcomm AI Stack SDK.
Participate in design discussions, code reviews, and testing cycles to ensure correctness, performance, and maintainability.
Learn and apply best practices in scalable AI software development under guidance from senior engineers.