NVIDIA
Deep Learning Solutions Architect – Inference Optimization(m/w/x)
Full-timeOn-siteSenior
Zürich
New Job?Nejo!
Your personal AI career agent
NVNVIDIA Switzerland AG
Solutions Architect, Cloud Inference Services(m/w/x)
Zürich
Full-timeOn-siteSenior
AI/ML
Data Science
Nejo AI Summary
Deploying E2E AI solutions for NVIDIA Cloud Partners, focusing on LLMs and Agentic Pipelines. Master's or Ph.D. in CS/AI or equivalent experience required. Support for AI services from training to inference.
Requirements
- Excellent verbal and written communication skills
- Excellent technical presentation skills in English
- Master's or Ph.D. in Computer Science or AI
- Equivalent experience in Computer Science or AI
- 5+ years industry/academic experience in ML/DL/Data Science
- Preference for DNN inference experience
- Work experience with modern LLM, VLM, diffusion architectures
- Emphasis on MoE architectures
- Understanding of DNN inference libraries
- Understanding of agentic pipeline development
- Excited to work with multiple levels and teams
- Collaboration with Engineering, Product, Sales, Marketing
- Strong analytical skills
- Strong problem-solving skills
- Self-starter drive for growth
- Passion for continuous learning
- Sharing findings across the team
- Strong time-management skills
- Strong organization skills
- Coordinating multiple initiatives and priorities
- Implementing new technology and products
- Experience with inference of large MoE architectures
- Experience with NLP, CV, or ASR inference
- Experience using DevOps technologies
- Understanding of HPC systems
- Understanding of data center design
- Understanding of high speed interconnect InfiniBand
- Understanding of Cluster Storage
- Understanding of Scheduling related design/management
Tasks
- Help NVIDIA Cloud Partners integrate AI stacks
- Develop and deploy E2E AI solutions
- Support AI services from training to inference
- Participate in projects involving LLMs, VLMs, Physical-AI, Agentic Pipelines
- Coordinate between customers, marketing, business development, and engineering
- Work on proof-of-concept demonstrations
- Lead discussions with developers, product teams, and executives
- Encourage adoption of NVIDIA’s AI technology platform
- Simplify deployment of AI technology to production
- Engage with different roles within NVIDIA and partners
- Understand NCPs' technology and provide solutions
- Develop and demonstrate NLP and LLM solutions
- Integrate solutions into agentic pipelines
- Perform in-depth GPU system analysis and optimization
- Optimize end-to-end agentic pipelines
- Partner with Engineering, Product, and Sales teams
- Develop and plan suitable solutions for customers
- Enable product feature growth through customer feedback
- Build industry expertise in AI Cloud solutions
- Contribute to integrating NVIDIA technology in Enterprise Computing
Work Experience
- 5 years
Education
- Master's degree
Languages
- English – Native
Tools & Technologies
- Machine learning
- Deep learning
- Data science
- DNN inference
- LLM
- VLM
- Diffusion architectures
- MoE
- TRT-LLM
- Dynamo
- RedHat Inference Server
- DevOps
- Docker
- Kubernetes
- Singularity
- HPC systems
- InfiniBand
- Cluster Storage
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of NVIDIA Switzerland AG and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
Not a perfect match?
- NVIDIA Switzerland AG
Senior HPC and AI Network Software Architect(m/w/x)
Full-timeOn-siteSeniorZürich - NVIDIA
HPC and AI Software Architect(m/w/x)
Full-timeOn-siteExperiencedZürich - NVIDIA Switzerland AG
Deep Learning Engineer, LLM Accuracy Evaluation(m/w/x)
Full-timeOn-siteSeniorZürich - NVIDIA
Senior GPU Networking Architect(m/w/x)
Full-timeOn-siteSeniorZürich
NVNVIDIA Switzerland AG
Solutions Architect, Cloud Inference Services(m/w/x)
Zürich
Full-timeOn-siteSenior
AI/ML
Data Science
Nejo AI Summary
Deploying E2E AI solutions for NVIDIA Cloud Partners, focusing on LLMs and Agentic Pipelines. Master's or Ph.D. in CS/AI or equivalent experience required. Support for AI services from training to inference.
Requirements
- Excellent verbal and written communication skills
- Excellent technical presentation skills in English
- Master's or Ph.D. in Computer Science or AI
- Equivalent experience in Computer Science or AI
- 5+ years industry/academic experience in ML/DL/Data Science
- Preference for DNN inference experience
- Work experience with modern LLM, VLM, diffusion architectures
- Emphasis on MoE architectures
- Understanding of DNN inference libraries
- Understanding of agentic pipeline development
- Excited to work with multiple levels and teams
- Collaboration with Engineering, Product, Sales, Marketing
- Strong analytical skills
- Strong problem-solving skills
- Self-starter drive for growth
- Passion for continuous learning
- Sharing findings across the team
- Strong time-management skills
- Strong organization skills
- Coordinating multiple initiatives and priorities
- Implementing new technology and products
- Experience with inference of large MoE architectures
- Experience with NLP, CV, or ASR inference
- Experience using DevOps technologies
- Understanding of HPC systems
- Understanding of data center design
- Understanding of high speed interconnect InfiniBand
- Understanding of Cluster Storage
- Understanding of Scheduling related design/management
Tasks
- Help NVIDIA Cloud Partners integrate AI stacks
- Develop and deploy E2E AI solutions
- Support AI services from training to inference
- Participate in projects involving LLMs, VLMs, Physical-AI, Agentic Pipelines
- Coordinate between customers, marketing, business development, and engineering
- Work on proof-of-concept demonstrations
- Lead discussions with developers, product teams, and executives
- Encourage adoption of NVIDIA’s AI technology platform
- Simplify deployment of AI technology to production
- Engage with different roles within NVIDIA and partners
- Understand NCPs' technology and provide solutions
- Develop and demonstrate NLP and LLM solutions
- Integrate solutions into agentic pipelines
- Perform in-depth GPU system analysis and optimization
- Optimize end-to-end agentic pipelines
- Partner with Engineering, Product, and Sales teams
- Develop and plan suitable solutions for customers
- Enable product feature growth through customer feedback
- Build industry expertise in AI Cloud solutions
- Contribute to integrating NVIDIA technology in Enterprise Computing
Work Experience
- 5 years
Education
- Master's degree
Languages
- English – Native
Tools & Technologies
- Machine learning
- Deep learning
- Data science
- DNN inference
- LLM
- VLM
- Diffusion architectures
- MoE
- TRT-LLM
- Dynamo
- RedHat Inference Server
- DevOps
- Docker
- Kubernetes
- Singularity
- HPC systems
- InfiniBand
- Cluster Storage
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of NVIDIA Switzerland AG and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
Like this job?
BetaYour Career Agent finds similar jobs for you every day.
About the Company
NVIDIA Switzerland AG
Industry
IT
Description
NVIDIA is a leading technology company specializing in Deep Learning, Artificial Intelligence, and Supercomputing.
Not a perfect match?
- NVIDIA
Deep Learning Solutions Architect – Inference Optimization(m/w/x)
Full-timeOn-siteSeniorZürich - NVIDIA Switzerland AG
Senior HPC and AI Network Software Architect(m/w/x)
Full-timeOn-siteSeniorZürich - NVIDIA
HPC and AI Software Architect(m/w/x)
Full-timeOn-siteExperiencedZürich - NVIDIA Switzerland AG
Deep Learning Engineer, LLM Accuracy Evaluation(m/w/x)
Full-timeOn-siteSeniorZürich - NVIDIA
Senior GPU Networking Architect(m/w/x)
Full-timeOn-siteSeniorZürich