About FAR Labs
FAR Labs is a unified platform for high-performance AI inference. We provide dedicated Inference and Model APIs with flexible workload placement—on our infrastructure, in a customer's cloud, on their hardware, or across shared GPUs.
Role
You'll set the technical direction for our inference stack and benchmarking practices. You'll make model serving faster and more efficient, validate those gains with credible benchmarks, and lead the engineers building alongside you.
What we're looking for
•Production experience with LLM inference-serving systems
•Expertise with vLLM, SGLang, TensorRT-LLM, or similar stacks
•Strong knowledge of batching, paged attention, KV-cache management, and modern serving architectures
•GPU performance engineering experience with CUDA or Triton
•Solid understanding of GPU utilisation, memory bandwidth, and precisions such as FP8 and FP4
This is an opportunity to shape the technology, performance standards, and engineering culture behind FAR Labs!
If this sounds like you, feel free to message me directly.
