Baseten
Product Manager, Inference Platform
$235K–$335K
San Francisco +1 · Hybrid · Manager · Full-time · Posted Apr 2, 2026
- Location
- San Francisco
New York - Experience
- 8+ years in product management.
About the job
Own the inference platform roadmap and end-to-end products that make production AI workloads scalable, reliable, and cost-efficient.
What you'll do
- Define workload autoscaling, placement, routing, and failover capabilities.
- Build safe rollout and incident-management features, including customer configuration and observability.
- Drive cross-functional roadmaps and improve inference latency, throughput, uptime, and cost efficiency.
What they ask for
- 8+ years in product management, including deep experience with infrastructure, distributed systems, or ML serving.
- Fluency reasoning about scaling, routing, failover, and cost/performance tradeoffs.
- Experience owning capabilities end to end, from backend through UX.
- Track record driving cross-team roadmaps and dependencies.
Nice to have
- Hands-on experience with GPU infrastructure.
- Experience with Kubernetes or serving frameworks such as vLLM, TensorRT-LLM, or SGLang.
Pay
$235K – $335K USD base salary
Tools
GPU infrastructure, Kubernetes, vLLM, TensorRT-LLM, SGLang
AI focus
Build and improve infrastructure for deploying, scaling, routing, and reliably serving AI models in production.
Model-written summary · the original posting is authoritative