Product Manager – BioNeMo Inference & AI Deployment

NVIDIA AI; Santa Clara (CA); On-site; USD 148,000 - 224,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a technical Product Manager for BioNeMo Inference to define and drive deployment, operation, and scaling of biomolecular AI inference workloads across cloud and on-prem environments.

You will collaborate with engineering, research, and platform teams to create production-ready experiences, build APIs/SDKs, and set metrics for adoption and performance while balancing open-source models, NVIDIA NIMs, and enterprise deployment strategy.

Qualifications

• 5+ years of industry experience, ideally including 3+ years in software engineering or a deeply technical role and 2+ years in product management.
• Master's degree (or equivalent experience) in Electrical, Mechanical, Materials, or other related fields.
• Demonstrated experience defining and shipping technical products, platforms, APIs, SDKs, developer tools, or cloud services.
• Strong understanding of AI/ML inference systems and deployment tradeoffs, including model serving, GPU infrastructure, batching, throughput, latency, scaling, and cost-performance optimization.
• Familiarity with containers and cloud-native infrastructure, including Docker, Kubernetes, Helm, CI/CD, and public-cloud deployment concepts.

Responsibilities

• Define product vision, strategy, and roadmap for BioNeMo inference products, including NIM-based deployment, performance optimization, scalability, and developer onboarding.
• Work closely with engineering, research, solution architects, cloud, and product teams to translate model capabilities into production-ready inference experiences.
• Define requirements for inference optimization: batching, throughput, latency, GPU utilization, multi-GPU and multi-node scaling, caching, scheduling, observability, and reliability.
• Partner with platform teams to ensure BioNeMo inference products deploy cleanly across cloud and enterprise environments, including Kubernetes-based environments.
• Develop the developer experience across APIs, SDKs, containers, Helm charts, reference architectures, documentation, and examples.
• Engage directly with early customers and partners to understand workflows, validate product direction, and turn feedback into prioritized requirements.
• Establish product metrics for adoption, usability, performance, and operational quality; use data and customer insight to improve the product.
• Drive cross-functional product launches with marketing, developer relations, sales, and solution architects.
• Help shape the product boundary between open-source biomolecular models, NVIDIA NIMs, and enterprise-ready deployment and support!

Skills

AI/ML inference

Cloud-native infra

Docker/Kubernetes

Product management

Developer experience

Education

Master's degree in Electrical, Mechanical, Materials, or related field

Tools

NVIDIA NIM

Triton

TensorRT-LLM

vLLM

Ray

KServe

Kubeflow

Docker

Kubernetes

CI/CD

Helm

Job description

NVIDIA is seeking a technical Product Manager for BioNeMo Inference to define and drive deployment, operation, and scaling of biomolecular AI inference workloads across cloud and on-prem environments.

You will collaborate with engineering, research, and platform teams to create production-ready experiences, build APIs/SDKs, and set metrics for adoption and performance while balancing open-source models, NVIDIA NIMs, and enterprise deployment strategy.