Software Engineer- Inference Platform

Baseten; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Baseten is looking for distributed systems engineers and generalists to build the distributed runtime powering large-scale LLM inference on Baseten. You’ll enable customers to deploy models with industry-leading performance, scalability, and reliability via Model APIs and hosted endpoints.

You’ll work across the stack—from developer experience used to deploy models to the systems that orchestrate deployments on Kubernetes and route traffic efficiently.

Responsibilities

• Build infra and orchestration for large-scale distributed LLM inference (routing, autoscaling, scheduling, runtime management).
• Design, build Model APIs with advanced inference: structured outputs, tool calling, and multimodal serving.
• Implement API versioning, validation, usage metering, quotas, and authentication.
• Instrument observability and benchmarks for speed, reliability, and quality.
• Define testing, release automation, and operational practices.
• Debug and harden production systems across Kubernetes, runtimes, networking, and GPU workloads.
• Collaborate with teams to roll out optimizations to customers.
• Own projects end to end from architecture to deployment and monitoring.

Job description

ABOUT BASETEN

BaseTen powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F, led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products.

THE ROLE

We're looking for distributed systems engineers and product-minded generalists to build the distributed runtime that powers large-scale LLM inference on Baseten. Our inference platform empowers customers to deploy and operate cutting-edge models with industry-leading performance, scalability, and reliability. It also powers Model APIs, our hosted endpoints for the latest open-source models. You'll work across the stack, from the developer experience customers use to deploy models, through the libraries behind features like tool calling and reasoning, down to the systems that orchestrate deployments on Kubernetes and route traffic efficiently. Your job is to make sure every model on our platform is fast, reliable, and cost-efficient. You'll join a small, high-impact team at the intersection of distributed systems, model performance, infrastructure, and product, helping define how developers use AI models at scale. This role is ideal for engineers who enjoy owning systems in production, solving hard integration problems, and making complex infrastructure simple and reliable for users.

EXAMPLE INITIATIVES

You'll get to work on these types of projects on our Inference Platform:The Baseten Inference Stack at NVIDIA Dynamo Day2x faster inference with KV cache-aware routingHow Baseten multi-cloud capacity management (MCM) unifies deployments

RESPONSIBILITIES

• Build the infrastructure and orchestration systems that deploy and run large-scale distributed LLM inference, including routing, autoscaling, scheduling, and runtime management.
• Design, build, and operate Model APIs, with a focus on advanced inference capabilities: structured outputs (JSON mode, grammar-constrained generation), tool/function calling, and multimodal serving.
• Implement platform fundamentals such as API versioning, validation, usage metering, quotas, and authentication.
• Instrument deep observability (metrics, traces, logs) and build repeatable benchmarks for speed, reliability, and quality.
• Help set best practices for testing, release automation, and operational excellence.
• Debug and harden complex production systems spanning Kubernetes, distributed runtimes, networking, and GPU workloads to improve reliability and scalability.
• Partner with Inference Performance engineers and other teams to make new optimizations broadly available to customers and easy to configure.
• Own projects end to end, from architecture through deployment, monitoring, and