Teams at Baseten

Manage and mature Baseten’s security governance, risk, compliance, privacy, audit, certification, vendor assessment, and customer assurance programs. Translate regulatory and customer requirements into technical controls and product requirements, partnering with Engineering, Product, Security, Legal, and Operations. Coordinate SOC 2, ISO, HIPAA, FedRAMP, and related audits; manage risk assessments, evidence collection, remediation, security questionnaires, training, and continuous improvement in a fast-growing AI platform company.

Develop and productionize high-performance LLM inference techniques across runtimes, scheduling, serving, routing, and GPU kernels. Profile and optimize latency, throughput, memory usage, and cost; support new models and hardware; build benchmarking frameworks; and contribute to open-source inference engines such as vLLM, SGLang, and TensorRT-LLM. The role requires strong programming, GPU architecture, ML library, and LLM optimization knowledge.

Build and operate the distributed inference platform powering large-scale LLM deployments. Responsibilities include orchestration, routing, autoscaling, scheduling, Model APIs, authentication, quotas, metering, observability, benchmarking, and production reliability across Kubernetes, networking, distributed runtimes, and GPU workloads. The role owns projects end to end and partners with performance engineers to deliver efficient, scalable AI inference capabilities and strong developer experiences.