Build and optimize ML serving infrastructure and pipelines using vLLM, ONNX, and PyTorch.
Originally posted 30 September 2026 by the employer.
About the role
Qualcomm is seeking a Senior Engineer - Machine Learning to design, develop, and optimize machine learning systems for enterprise platforms and applications. The position focuses on model development, inference optimization, and scalable ML infrastructure.
What you'll do
- Design and implement machine learning models, pipelines, and training, evaluation, and deployment workflows for production use.
- Develop reusable ML components, libraries, and frameworks.
- Optimize model inference for latency, throughput, and cost using caching, quantization, batching, and routing.
- Benchmark and profile models across diverse workloads and hardware environments.
- Integrate ML and LLM models into APIs, microservices, and applications while maintaining model-serving infrastructure such as vLLM, ONNX, and custom runtimes.
- Design data pipelines for ingestion, preprocessing, feature engineering, and validation.
What you'll need
- Strong programming skills in Python and at least one systems language (C++, Rust, or Go).
- Solid understanding of machine learning fundamentals, transformer architectures, LLMs, and model evaluation and debugging.
- Experience with ML frameworks such as PyTorch or TensorFlow.
- Experience with model deployment and serving systems, as well as building scalable software and APIs.
Nice to have
- Experience with Large Language Models (LLMs), multimodal models, or generative AI.
- Experience with retrieval systems and RAG pipelines.
- Experience with distributed computing and GPU/accelerator environments, including model serving and cache/state management (such as KV cache and embeddings) across disaggregated systems.
- Experience with Kubernetes, Docker, and CI/CD pipelines.
- Experience with agentic and multi-step AI workflows, tool integration, orchestration, and multi-component pipelines.
- Knowledge of model optimization techniques (quantization, distillation, caching), vector databases (OpenSearch, Qdrant), and cost-aware system design (model routing, dynamic batching).
Skills: PyTorch, Model Serving, Inference Optimization, Python, Quantization, Docker
More semiconductor jobs: Qualcomm jobs · San Diego jobs
First seen in our index 42 days ago, well below the 56-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · Infrastructure Platform
|
Open roles in category
1040
|
Median days since first seen
56 d
|
Category median salary (all employers)
$236k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | Qualcomm | All employers we track in this specialty (1040 roles · 93 employers) |
|---|---|---|
| Open roles in this specialty | 60 | 1040 |
| Open roles in the wider Software, Firmware & Systems family | 731 | 6684 · 161 employers |
| Median days since first seen | 59 d | 56 d (−3 d vs this employer) |
| Median salary (USD postings) | n/a | $236k |
Skills observed across this category: PyTorch, Model Serving, Inference Optimization, Python, Quantization, Docker
Who's hiring in this category
- NVIDIA · 350 open roles · median 61 d
- AMD · 56 open roles · median 36 d
- Qualcomm (this employer) · 56 open roles · median 62 d
- Graphcore · 47 open roles · median 118 d
- Arm Holdings · 38 open roles · median 15 d
- Intel Corporation · 37 open roles · median 23 d
How we counted: 1040 open Infrastructure/Platform Software (Infrastructure Platform) roles from 93 employers tracked in the SemiconductorJobs index, counted 12 Nov 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there, and is counted in the wider Software, Firmware & Systems family row. Days are counted from when our index first saw each posting, not from the employer's original posting date.