Product Manager - BioNeMo Inference
Core
Lead the definition, strategy, and execution of BioNeMo Inference products to enable developers and researchers to deploy, operate, and scale biomolecular AI inference workloads on NVIDIA NIM and accelerated computing.
Role type
Senior technical Product Manager (AI Infrastructure & Developer Platforms)
Builds
Production-ready inference experiences, APIs, SDKs, containers, Helm charts, reference architectures, and documentation for biomolecular AI models.
Domain
AI Infrastructure / Generative AI / Biomolecular Research / Cloud Computing
Deliverable
production ML models
Required skills
AI/ML inference systems, model deployment, GPU infrastructure, batching, throughput, latency, scaling, cost-performance optimization, containers, cloud-native infrastructure, Kubernetes, Docker, Helm, CI/CD, product strategy, roadmap management, customer discovery, system architecture.
Preferred skills
AI inference orchestration platforms (NVIDIA NIM, Triton, TensorRT-LLM, vLLM, Ray, KServe, Kubeflow), MLOps, open-source product building, biomolecular/scientific foundation models.
Technologies
NVIDIA NIM, Triton, TensorRT-LLM, vLLM, Ray, KServe, Kubeflow, Kubernetes, Docker, Helm, CI/CD
Responsibilities
Define product vision, strategy, and roadmap for BioNeMo inference products; translate model capabilities into production-ready inference experiences; define requirements for inference optimization (batching, throughput, latency, GPU utilization, multi-GPU/multi-node scaling, caching, scheduling, observability, reliability); partner with platform teams to ensure clean deployment across cloud and enterprise environments; develop developer experience across APIs, SDKs, containers, Helm charts, reference architectures, documentation, and examples; engage directly with early customers and partners to validate product direction; establish product metrics for adoption, usability, performance, and operational quality; drive cross-functional product launches.
Seniority
Senior, hands-on IC
