Senior Staff AI Systems Engineer On-Device Model Enablement

Blumberg Capital Company

San Diego (CA)

On-site

USD 194,000 - 292,000

Full time

3 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Qualcomm Technologies, Inc. is seeking a Senior Staff Software Engineer to provide technical leadership for bringing state-of-the-art AI models to Snapdragon platforms using Qualcomm's AI software stack.

You will lead analysis, adaptation, optimization, quantization, compilation, and on-device execution for LLMs, LVMs, VLMs, and LMMs with close collaboration across AI Research, hardware/software, and product teams.

Qualifications

  • Bachelor’s degree in Computer Science, Computer Engineering, Electrical Engineering, or related field with 8+ years of software delivery experience.
  • OR Master’s or PhD with 6+ years of experience in software design and delivery.
  • At least 5 years hands-on experience in AI/ML software development, model inference or compiler tech.

Responsibilities

  • Lead the bring-up and enablement of new LLM, LVM, VLM, and multimodal model architectures on Snapdragon platforms.
  • Partner with AI Research teams to understand model architecture, tensor flows, attention and cache behavior, model inputs and outputs, and performance-sensitive computation patterns.
  • Analyze model graphs and identify operator-level, graph-level, precision, memory, and runtime gaps against Qualcomm's AI accelerator backends.
  • Own the architecture and design of scalable model-enablement solutions, including component boundaries, APIs, stage contracts, configuration schemas, artifact interfaces, extensibility mechanisms, and integration across model, quantization, compiler, and runtime systems.
  • Define scalable approaches for model re-authoring, graph adaptation, graph lowering, decomposition, fusion, layout transformation, and backend-specific optimization.
  • Architect reusable model-enablement solutions instead of model-specific workarounds, and integrate them into Qualcomm's AI software stack and model-enablement frameworks.
  • Lead the design of declarative and extensible pipeline capabilities, including reusable stages, model mappings, quantization recipes, configuration interfaces, artifact handoffs, caching, validation, and execution workflows.
  • Develop and optimize model preparation, quantization, calibration, export, compilation, and on-device execution flows.
  • Apply quantization techniques such as PTQ, QAT, mixed precision, weight and activation quantization, blockwise/groupwise quantization, calibration, and accuracy-recovery optimization.
  • Evaluate accuracy, latency, throughput, memory usage, model size, and power efficiency across FP, prepared, quantized, compiled, and on-device checkpoints.
  • Guide enablement of advanced Generative AI features such as KV-cache optimization, prefill and decode graphs, LoRA, MoE, speculative decoding, multimodal processing, and vision encoders.
  • Debug complex issues across model architecture, PyTorch and ONNX graphs, quantization, compiler, runtime, OS, and hardware layers.
  • Establish technical plans, divide work, manage risks, and drive multiple model-enablement initiatives from investigation to production.
  • Participate in and lead architecture reviews, design reviews, code reviews, and performance/accuracy reviews.
  • Mentor engineers and establish engineering practices for maintainable AI software.
  • Communicate technical strategy, status, dependencies, and risks to leadership and stakeholders.

Skills

AI/ML software
Python
C/C++
PyTorch
ONNX
Leadership

Education

Bachelor’s degree
Master’s degree
PhD

Tools

PyTorch
ONNX
CMake

Job description

Qualcomm Technologies, Inc. is seeking a Senior Staff Software Engineer to provide technical leadership for bringing state-of-the-art AI models to Snapdragon platforms using Qualcomm's AI software stack.

You will lead analysis, adaptation, optimization, quantization, compilation, and on-device execution for LLMs, LVMs, VLMs, and LMMs with close collaboration across AI Research, hardware/software, and product teams.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior AI Model Enablement Engineer: LLM/LVM on Edge
Senior AI Model Enablement Engineer: LLM/LVM on Edge

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 194,000 - 292,000
Discretionary bonus
RSU grants
Senior AI Model Enablement Engineer - On-Device & Tools
Senior AI Model Enablement Engineer - On-Device & Tools

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 194,000 - 292,000
AI Model Enablement Engineer – On-Device ML Tools
AI Model Enablement Engineer – On-Device ML Tools

Blumberg Capital Company • San Diego (CA)

On-site
USD 141,000 - 211,000
Senior AI Model Enablement Engineer – On-Device ML Tools
Senior AI Model Enablement Engineer – On-Device ML Tools

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 141,000 - 211,000
Benefits package
RSU grants
Annual bonus
Senior Staff ML Engineer: On-Device AI & Runtime Leader
Senior Staff ML Engineer: On-Device AI & Runtime Leader

Blumberg Capital Company • San Diego (CA)

On-site
USD 194,000 - 292,000
Competitive benefits package
Senior Embedded ML Engineer - On-Device AI
Senior Embedded ML Engineer - On-Device AI

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 224,000 - 335,000
Senior Staff ML Engineer - Edge AI & On-Device Systems
Senior Staff ML Engineer - Edge AI & On-Device Systems

QUALCOMM, Inc. • San Diego (CA)

Hybrid
USD 194,000 - 292,000
Senior Embedded ML Engineer – On-Device AI
Senior Embedded ML Engineer – On-Device AI

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 224,000 - 335,000
AI Hardware Performance Modeling Engineer for LLMs
AI Hardware Performance Modeling Engineer for LLMs

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 162,000 - 243,000
Senior AI Systems Architect - On-Device Frameworks
Senior AI Systems Architect - On-Device Frameworks

QUALCOMM, Inc. • San Diego (CA)

On-site
USD 217,000 - 325,000