Staff AI Performance Engineer - Cloud Inference & GenAI

SAM Seamless Network

San Diego (CA)

Sur place

USD 194 000 - 292 000

Plein temps

Il y a 6 jours
Soyez parmi les premiers à postuler

Obtenez une réponse de cet employeur

Votre CV et votre lettre de motivation, adaptés exactement à ce que l’employeur recherche.

Passez les filtres ATS

Résumé du poste

Qualcomm Technologies, Inc. is seeking an AI Performance Engineer (Cloud AI Engineering) to advance inference acceleration for GenAI workloads. You will optimize models using PyTorch and ONNX, craft high-level kernels in Triton, and collaborate with compiler, firmware, and platform teams.

The role requires strong Python, deep transformer knowledge, and experience mapping workloads across ML accelerators and distributed systems. Advanced degrees (MS or PhD) in CS/ML/CE/EE are preferred.

Qualifications

  • MS or PhD in CS/ML/CE/EE or related field.
  • Strong Python and PyTorch experience in production environments.
  • Deep understanding of transformer architectures and attention mechanisms.

Responsabilités

  • Convert, optimize and deploy models for efficient inference using PyTorch/ONNX.
  • Design high-level kernels (e.g., in Triton) for efficient code generation.
  • Analyze and optimize LLM/VLM/diffusion model performance for latency/throughput.
  • Map AI workloads across current and future hardware architectures.
  • Collaborate with compiler, firmware and platform teams to drive solutions.

Connaissances

Python
PyTorch
ONNX
Transformer models
Workload mapping
Distributed systems
ML accelerators
In‑memory processing

Formation

MS in CS/ML/CE/EE
PhD in CS/CE/ML

Outils

Triton

Description du poste

Qualcomm Technologies, Inc. is seeking an AI Performance Engineer (Cloud AI Engineering) to advance inference acceleration for GenAI workloads. You will optimize models using PyTorch and ONNX, craft high-level kernels in Triton, and collaborate with compiler, firmware, and platform teams.

The role requires strong Python, deep transformer knowledge, and experience mapping workloads across ML accelerators and distributed systems. Advanced degrees (MS or PhD) in CS/ML/CE/EE are preferred.

Obtenez votre examen gratuit et confidentiel de votre CV.

ou faites glisser et déposez votre fichier ici.

Similar jobs

Postes similaires à comparer

Senior/Staff AI Performance Engineer: Inference Optimization
Senior/Staff AI Performance Engineer: Inference Optimization

Qualcomm • San Diego (CA)

Sur place
USD 178 400 - 267 600
Competitive annual discretionary bonus
RSU grants
Highly competitive benefits package
AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff
AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff

Qualcomm • San Diego (CA)

Sur place
USD 178 400 - 267 600
Competitive annual discretionary bonus
RSU grants
Highly competitive benefits package
Principal AI Systems Engineer - LLM Inference (Cloud)
Principal AI Systems Engineer - LLM Inference (Cloud)

Qualcomm • San Diego (CA)

Sur place
USD 224 000 - 335 000
AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff
AI Performance Engineer (Cloud AI Engineering), Sr | Staff | Sr. Staff

SAM Seamless Network • San Diego (CA)

Sur place
USD 194 000 - 292 000
Datacenter AI Systems Engineer: GenAI & ML Innovator
Datacenter AI Systems Engineer: GenAI & ML Innovator

Blumberg Capital Company • San Diego (CA)

Sur place
USD 118 000 - 177 000
Datacenter AI Systems Engineer: GenAI & ML Solutions
Datacenter AI Systems Engineer: GenAI & ML Solutions

Qualcomm • San Diego (CA)

Sur place
USD 111 300 - 166 900
Edge AI Engineer: On-Device GenAI & Model Optimization
Edge AI Engineer: On-Device GenAI & Model Optimization

SAM Seamless Network • San Diego (CA)

Sur place
USD 123 000 - 184 000
Data Center AI Systems Engineer
Data Center AI Systems Engineer

Qualcomm • San Diego (CA)

Sur place
USD 111 300 - 166 900
Datacenter AI Systems Engineer — ML/GenAI + Hardware
Datacenter AI Systems Engineer — ML/GenAI + Hardware

QUALCOMM, Inc. • San Diego (CA)

Sur place
USD 118 000 - 177 000
Annual discretionary bonus
RSU grants
Competitive benefits package
Senior AI Accelerator Architect for Scalable Training
Senior AI Accelerator Architect for Scalable Training

QUALCOMM, Inc. • Santa Clara (CA)

Sur place
USD 127 000 - 190 000