Jobs at Baseten

As a Forward Deployed Engineer, you will develop and maintain ML solutions, collaborate with teams on AI/ML pipelines, and manage projects end-to-end.

Lead and mentor a team of Forward Deployed Engineers in building and optimizing LLM inference workloads, delivering high-performance AI applications, and collaborating with cross-functional teams.

The role involves developing and managing infrastructure for distributed LLM inference systems, ensuring performance and usability, debugging complex systems, and collaborating with performance engineers.

Design and implement RDMA/InfiniBand networking primitives for distributed GPU inference, optimize communication for Disaggregated KV Cache and WideEP, enable sub-10s model startup, validate hardware performance on H100/H200/B200/B300/GB300 clusters, build observability tools, and optimize or author communication kernels (NCCL/NVSHMEM/UCX).

As a Software Engineer, you'll build and maintain Baseten's core product, design APIs, implement features, fix issues, and collaborate with teams.

Develop and maintain components for machine learning inference platform. Focus on Kubernetes deployments, resource management, and performance monitoring.

As a Software Engineer in the Platform Team, you will build internal tooling and infrastructure to enhance productivity, collaboration, and quality across engineering teams.

Own and operate Baseten's internal AI stack, build and deploy custom AI agents and LLM-powered tools, evaluate third-party AI developer tools, instrument usage and measure impact on engineering productivity, and support engineering teams in adopting AI workflows.

Build and maintain responsive, accessible frontend interfaces using React and TypeScript. Collaborate with product, design, and backend teams to launch performant, scalable UIs, create reusable component libraries, define APIs, mentor engineers, and drive frontend best practices.

Build an internal AI developer platform that provisions agent configs, context tooling, eval harnesses, and rollout mechanics to make AI-assisted engineering the default. Integrate LLMs and third-party coding tools, enable self-serve agent creation, embed safety and audit controls, and measure impact on developer productivity.

The GPU Kernel Engineer will design and implement high-performance GPU kernels, optimize code, and collaborate with research teams to enhance AI workloads.

Lead development of enterprise platform features focusing on infrastructure, security, and compliance for enterprise customers. Oversee projects, collaborate cross-functionally, and mentor engineering teams.

As an AI Support Engineer, you'll manage support requests, resolve user issues, optimize ML models, and contribute to product development.

Partner with Sales and customers to run technical discovery, lead demos and scoping, design repeatable ML inference deployments across modalities, benchmark inference performance, and drive POC execution and stakeholder alignment.

As a Site Reliability Engineer, you'll build and maintain infrastructure for ML models, automate processes, and collaborate cross-functionally.

The OS / K8s Systems Engineer will build and automate systems to turn GPU hardware into production-ready compute, focusing on reproducibility, scalability, and reliability across data centers.

Build and evolve scalable observability systems: high-throughput telemetry ingest, cost-efficient storage, instrumentation libraries, SLO/alerting infrastructure, and integrations to improve reliability, diagnostics, and incident response across multi-cloud infrastructure.

The Software Engineer will lead the development of Baseten Voice AI, focusing on real-time model serving systems, collaboratng with teams on architecture and implementation.

Partner with customers to architect, build, and deploy high-scale production AI applications. Translate ambiguous goals into reliable, observable services, implement end-to-end model deployment and monitoring, optimize ML projects, and own customer-facing technical delivery and product outcomes.

Lead design and build of a real-time observability and root-cause analysis system for high-density GPU fabrics. Collect, reduce, correlate telemetry from switches, hosts, NICs, GPUs, and services; model topology and ownership; separate fabric faults from host/driver/RDMA/scheduler issues; and produce operator workflows for triage and remediation.