GenAI Solutions Architect – Inference & AIOps

Nvidia Corporation in; Santa Clara (CA); On-site; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity and benefits

Travel opportunities

Job summary

NVIDIA is seeking an experienced Senior Solutions Architect to implement Generative AI deployment and MLOps strategies for finance-focused use cases. You will serve as a trusted technical advisor, working with customers to design NVIDIA-based AI solutions, optimize inference workloads on Kubernetes, and contribute to proof-of-concepts and performance analyses.

Requires 8+ years in DL frameworks, strong Python skills, and expertise in GPU orchestration and MIG, plus experience with TensorRT and

Qualifications

• BS, MS or PhD in Computer Science or related field (or equivalent experience).
• 8+ years of hands-on experience with PyTorch and TensorFlow.
• Strong Python programming, debugging and software design skills.
• Experience with GPU orchestration and MIG management within Kubernetes.
• Experience with containerization, monitoring and observability for AI deployments.
• Knowledge of LLM and DL inference theory and practice.
• Excellent presentation and collaboration abilities.

Responsibilities

• Partner with solution teams to define high-value AI solutions.
• Engage with developers, researchers and data scientists across domains.
• Collaborate with lighthouse customers and partners for platform adoption.
• Help customers build NVIDIA-based AI solutions and MLOps workflows.
• Analyze AI inference performance and power usage on Kubernetes.
• Travel to conferences and customer sites as needed (up to 20%).

Skills

Python programming

Deep Learning frameworks

GPU optimization

Communication skills

Problem-solving

Education

BS/MS/PhD in CS or related fields

Tools

NVIDIA NIM

Dynamo

TensorRT

TensorRT-LLM

Job description

NVIDIA is seeking an experienced Senior Solutions Architect to implement Generative AI deployment and MLOps strategies for finance-focused use cases. You will serve as a trusted technical advisor, working with customers to design NVIDIA-based AI solutions, optimize inference workloads on Kubernetes, and contribute to proof-of-concepts and performance analyses.

Requires 8+ years in DL frameworks, strong Python skills, and expertise in GPU orchestration and MIG, plus experience with TensorRT and