Build foundational observability infrastructure, including high-throughput telemetry pipelines, storage, instrumentation, alerting, and SLO systems across multi-cloud environments. The role requires strong programming skills in Python, Rust, or Go and experience with observability platforms and large-scale data systems.
Owns end-to-end billing, pricing, and revenue infrastructure at Baseten, building scalable systems and internal tools. Requires 5+ years software experience, billing/internal tools background, and deep web/databases knowledge.
Software engineer architecting GPU networking software with RDMA for distributed AI inference. Optimizes communication for H100/Blackwell clusters, WideEP, and serverless LLM startups using C++/Python and NVIDIA tools.
Builds and optimizes Model APIs for high-performance AI model serving, focusing on inference capabilities, low-latency backend services, and GPU optimizations. Requires 3+ years in distributed systems with strong performance debugging skills.
Develops and optimizes high-performance GPU kernels for AI/ML operations like matrix multiplications and attention mechanisms using CUDA and C++. Requires deep GPU architecture knowledge, performance profiling, and low-level optimization expertise.
Build foundational observability infrastructure, including high-throughput telemetry pipelines, storage, instrumentation, alerting, and SLO systems across multi-cloud environments. The role requires strong programming skills in Python, Rust, or Go and experience with observability platforms and large-scale data systems.
Owns end-to-end billing, pricing, and revenue infrastructure at Baseten, building scalable systems and internal tools. Requires 5+ years software experience, billing/internal tools background, and deep web/databases knowledge.
Software engineer architecting GPU networking software with RDMA for distributed AI inference. Optimizes communication for H100/Blackwell clusters, WideEP, and serverless LLM startups using C++/Python and NVIDIA tools.
Builds and optimizes Model APIs for high-performance AI model serving, focusing on inference capabilities, low-latency backend services, and GPU optimizations. Requires 3+ years in distributed systems with strong performance debugging skills.
Develops and optimizes high-performance GPU kernels for AI/ML operations like matrix multiplications and attention mechanisms using CUDA and C++. Requires deep GPU architecture knowledge, performance profiling, and low-level optimization expertise.