Member of Technical Staff, Inference

San Francisco$300k - $400kFull-timePosted 4mo ago

About the role

Engineer to own inference systems powering models in production and research, spanning from serving infrastructure to hardware-level optimization.

Design and build high-throughput, low-latency inference serving systems for frontier models, optimizing for both research iteration and production deployment
Optimize inference performance across GPU and accelerator hardware - maximizing FLOPs utilization, memory bandwidth, and compute efficiency for large-scale models
Enable and extend distributed inference frameworks (e.g. vLLM, SGLang, TensorRT-LLM) to support novel architectures, long-context workloads, and agentic inference patterns
Implement and validate inference-time optimizations: speculative decoding, quantization, KV cache management, and batching strategies
Build observability and reliability infrastructure so the team can measure latency, throughput, and cost across every serving configuration
Partner directly with teams to bring new model architectures and post-training techniques into production quickly

Experience with inference systems for frontier models in production/research
Strong background in serving infrastructure and hardware-level optimization
Track record with GPU/accelerator optimization, distributed inference
Familiarity with inference frameworks (e.g., vLLM, SGLang, TensorRT-LLM) and optimization techniques

Required:Inference system designHardware acceleration optimization

Nice to have:Distributed inference frameworksInference-time optimizations

Last updated Aug 27, 2026. Interested? Apply on the company site.

Mirendil — a frontier lab building systems that excel at AI R&D.

AI R&Dfrontier AIdemocratize frontier AI R&Dsystems that excel at AI R&D