Inference is everything. Baseten is an AI infrastructure platform giving you the tooling, expertise, and hardware needed to bring great AI products to market - fast. Our proprietary Inference Stack utilizes the cutting-edge of performance research combined with highly performant and reliable infrastructure to give you out-of-the-box global availability with 99.99% of uptime.
On-site · Montréal
Build and operate the distributed infrastructure and APIs that deploy, route, and serve large-scale LLM inference, including capabilities such as structured outputs, tool calling, and multimodal serving. Own projects end to end, improving performance, reliability, observability, and developer experience while collaborating across infrastructure and inference teams.
On-site · Montréal
Implement and optimize production LLM inference across runtimes, kernels, scheduling, serving, and routing, using techniques such as quantization, speculative decoding, and KV-cache management. Improve latency, throughput, GPU utilization, and cost; benchmark new models and hardware; and contribute to open-source inference engines while collaborating across teams.