Senior Engineer – AI Model Enablement & Software Tools

Qualcomm • San Diego, CA

5d • $140,800 - $211,200

About The Position

As an Engineer or Senior Engineer on Qualcomm’s AI Stack SDK Software team, you will help bring modern AI models to Snapdragon platforms using Qualcomm’s AI software stack and model-enablement frameworks. You will work with senior engineers to analyze, adapt, optimize, quantize, compile, and validate language, vision, vision-language, and multimodal models. The role involves collaboration with AI Research and AI accelerator hardware and software teams to understand model architectures, identify operator- and graph-level backend gaps, and integrate reusable solutions into Qualcomm’s frameworks and SDK.

The position combines AI/ML software development with graph processing, model optimization, systems software, and on-device execution. Work includes model loading, graph adaptation, quantization, calibration, compilation, runtime integration, performance analysis, and debugging across software and hardware layers. Engineers work under technical-lead guidance; Senior Engineers take greater ownership of feature design, implementation, debugging, and delivery.

Requirements

• Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• For Engineer: project or internship experience for entry-level candidates, or 1+ years of software development experience.
• For Senior Engineer: 2+ years of experience in software design, development, and delivery.
• Good programming skills in Python and/or C/C++.
• Strong software engineering fundamentals, including data structures, algorithms, object-oriented design, debugging, testing, and source control.
• Foundational understanding of AI/ML concepts, including neural networks, deep learning, model inference, and common model execution workflows.
• Practical experience using agentic coding tools such as Claude Code, OpenAI Codex, or equivalent tools for code exploration, implementation, testing, and debugging, with the ability to review and validate generated code.
• Ability to read and understand unfamiliar software and model implementations.
• Strong analytical and debugging skills, including structured root-cause analysis.
• Ability to collaborate effectively within a team and communicate technical concepts clearly.
• Ability and willingness to learn model architectures, graph processing, quantization, compiler, runtime, and hardware-aware optimization concepts.
• The additional minimum qualifications section specifies a bachelor’s degree in Computer Science, Engineering, Information Systems, or a related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience; or a master’s degree in those fields and 1+ year of related work experience; or a PhD in those fields.

Nice To Haves

• Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
• Coursework, internship, project, or professional experience involving AI/ML inference, model optimization, or embedded AI software.
• Familiarity with PyTorch, ONNX, Hugging Face Transformers, or related AI/ML frameworks.
• Familiarity with graph-based model representations and tooling such as ONNX, TorchScript, MLIR, ONNX Runtime, ExecuTorch, or TFLite/LiteRT.
• Basic understanding of model quantization and calibration, including PTQ, QAT, weight and activation quantization, and mixed precision.
• Experience or coursework involving transformer-based models, LLMs, vision models, or multimodal models.
• Understanding of common transformer components such as attention, normalization, feed-forward layers, positional encoding, and KV cache.
• Experience with Linux-based software development.
• Experience developing or optimizing embedded, mobile, edge, or system-level software.
• Exposure to Android or an RTOS environment such as QNX.
• Familiarity with CMake-based builds, Git-based source control, code reviews, and agile software development practices.
• Experience writing unit tests and integration tests, and debugging software across multiple abstraction layers.
• Exposure to model performance analysis, profiling, memory optimization, or hardware accelerator programming.
• User-level or development exposure to commercial AI software stacks and model-enablement frameworks, including model conversion, optimization, compilation, deployment, and runtime tools.
• Exposure to Snapdragon SoCs, NPUs, HTPs, or other AI accelerator architectures.

Responsibilities

• Contribute to bringing up and enabling new language, vision, vision-language, and multimodal models on Snapdragon platforms.
• Study model implementations and computational graphs, including inputs, outputs, operators, tensor shapes, data flow, and execution behavior.
• Work with AI Research and backend teams to identify unsupported operators, graph patterns, precision constraints, and performance limitations.
• Implement model re-authoring, operator decomposition, graph transformations, layout changes, and backend-specific adaptations.
• Develop reusable model support for Qualcomm’s model-enablement frameworks.
• Implement and maintain pipeline stages, model mappings, quantization recipes, configuration models, artifact handling, and validation utilities.
• Convert, optimize, and export PyTorch and ONNX models for compilation and execution on Qualcomm AI accelerators.
• Apply and validate quantization and calibration flows, including weight and activation quantization, mixed precision, PTQ, and accuracy-recovery techniques.
• Measure and improve model accuracy, latency, throughput, memory consumption, model size, and power efficiency.
• Work with generative AI inference concepts such as transformer attention, KV cache, prefill and decode execution, LoRA, MoE, and speculative decoding.
• Support vision and multimodal processing flows, including image processors, vision encoders, language backbones, and cross-component artifact integration.
• Debug issues across model code, computational graphs, quantization, compiler, runtime, operating system, and hardware layers.
• Develop unit, integration, accuracy, performance, and on-device validation tests.
• Write high-quality, maintainable, and well-documented Python and C/C++ code.
• Participate in technical discussions, design reviews, code reviews, debugging sessions, and testing cycles.
• Collaborate with globally distributed engineering, research, hardware, QA, product, and customer-facing teams.
• Senior Engineers independently own larger features, contribute to design decisions, mentor junior engineers, and drive assigned model-enablement work through completion.

Benefits

• Competitive annual discretionary bonus program.
• Opportunity for annual RSU grants; employees on sales-incentive plans are not eligible for the annual bonus.
• Competitive benefits package designed to support employees at work, at home, and at play.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level