← Zurück zur Liste

Stelle
· Principal
Principal SW Engineer – LLM Serving (Cloud AI)
Sonstige
• Principal
• Vor Ort
• Vollzeit
•
San Diego, USA
Qualcomm's Cloud AI team is developing software solutions for inference acceleration and is seeking an engineer who has delivered commercial software with experience spanning design, compiler technology, performance modeling and bottleneck analysis. The role spans the whole product life cycle from early R&D to commercial deployment.
Responsibilities
- ▹Plan, manage and deliver large commercial software projects
- ▹Work with serving frameworks such as vLLM
- ▹Develop in PyTorch
- ▹Understand and apply LLMs, multi-modal and reasoning models
- ▹Execute, analyze and optimize neural networks
- ▹Write high-performance software for multicore systems
- ▹Develop in C++ and Python
- ▹Analyze performance of software/hardware solutions on multi-core architectures (core, cache, memory, bus, PCIe)
- ▹Apply understanding of multi-core processor and SoC architectures (NoCs, caches, memories)
- ▹Perform performance modeling of SoC architectures
Requirements
- ▹Bachelor's degree in Computer Science, Engineering, Information Systems or related field and 8+ years of Hardware/Software/Systems Engineering experience (or Master's + 7 years, or PhD + 6 years)
Nice to have
- ▹Proven ability to plan, manage and deliver large commercial software projects
- ▹Experience with serving frameworks like vLLM
- ▹Strong development skills in PyTorch
- ▹Strong understanding of LLMs, multi-modal and reasoning models
- ▹Experience executing, analyzing and optimizing neural networks
- ▹Experience writing high-performance software for multicore systems
- ▹Experience with C++ and Python
- ▹Strong skills analyzing performance of software/hardware solutions on multi-core architectures; understanding of multi-core fundamentals (core, cache, memory, bus, PCIe)
- ▹Understanding of multi-core processor and SoC architectures (NoCs, caches, memories)
- ▹Experience with performance modeling of SoC architectures
- ▹Excellent written and verbal communication skills, team player
- ▹Experience with machine learning accelerators and related software highly desired
- ▹Background in neural network operators and mathematical operations (linear algebra, math libraries)
- ▹Master's in Computer Engineering and/or Computer Networks & Systems and/or Computer Science
Soft skills
CommunicationTeam player attitudeProject management ability
What we offer
- ▹Pay range: $200,800-$301,200
- ▹Annual discretionary bonus program
- ▹Opportunity for annual RSU grants
- ▹Competitive benefits package
About the company
Qualcomm's Cloud AI team develops software solutions for inference acceleration.
Education: BSc+8 év / MS+7 év / PhD+6 év, számítástechnika, mérnöki, információs rendszerek vagy kapcsolódó területen; mesterdiploma preferált.
Ähnliche Stellen

Stelle
· Principal
Principal Engineer, Software Development Engineering (Apps)
Sandisk
AI/MLCppData Science
+15
💰 Gehalt: keine Angabe
🏢 Vor Ort
Milpitas
🗣️ EN

Stelle
· Principal
Principal Engineer, Software Development Engineering (Apps)
Sandisk
AI/MLCppData Science
+15
💰 Gehalt: keine Angabe
🏢 Vor Ort
Milpitas
🗣️ EN

Stelle
· Principal
Member of Technical Staff, Cloud Infrastructure
Fireworks AI
AI/MLArgocd
+10
151 299–190 205 €/Jahr
brutto
🏢 Vor Ort
New York
🗣️ EN

Stelle
· Principal
Member of Technical Staff
Fireworks AI
AI/MLFlink
+16
151 299–190 205 €/Jahr
brutto
🏢 Vor Ort
New York
🗣️ EN

Stelle
· Principal
Member of Technical Staff
Fireworks AI
AI/MLFlinkCpp
+14
💰 Gehalt: keine Angabe
🏢 Vor Ort
New York
🗣️ EN

Stelle
· Principal
Member of Technical Staff, Cloud Infrastructure
Fireworks AI
AI/MLArgocdCpp
+8
💰 Gehalt: keine Angabe
🏢 Vor Ort
San Mateo
🗣️ EN