Member of Technical Staff, Inference

About the role

Radical Numerics is seeking a Member of Technical Staff, Inference to build and optimise systems that bring cutting‑edge biological AI models into production. You will work at the intersection of AI systems, distributed computing and model deployment to deliver high‑performance inference for large‑scale genome and multimodal models.

Key responsibilities

• Identify and eliminate bottlenecks across the inference stack, from model execution and memory management to networking, scheduling and hardware utilisation.
• Develop high‑performance inference primitives, including GPU kernels, numerical operators and serving infrastructure for modern accelerator platforms.
• Partner with external customers such as pharmaceutical companies, biotech organisations and government partners to deploy models in production environments.
• Build scalable deployment infrastructure for serving, monitoring, benchmarking and operating foundation models across cloud, enterprise and secure environments.
• Collaborate with research and platform teams to ensure new model architectures can be efficiently deployed at scale.

Required profile

• Proven experience optimizing, deploying and operating large language models or other foundation models in production.
• Strong performance‑engineering and kernel‑development skills with deep understanding of GPU architectures.
• Systems‑level thinking ability to diagnose and solve bottlenecks across the full stack.
• Hands‑on builder with solid software‑engineering fundamentals in Python and modern ML frameworks such as PyTorch.
• Excellent technical communication and ability to work with cross‑functional research, engineering and scientific teams.

Required skills

• Python
• PyTorch
• CUDA or Triton
• GPU kernel optimisation
• Inference frameworks (e.g., vLLM, TensorRT‑LLM, SGLang, DeepSpeed)