Member of Technical Staff, Inference

About the Role

As a Member of Technical Staff, Inference at Radical Numerics, you will build and optimize the systems that bring frontier biological AI models into production. Your work will focus on delivering state-of-the-art inference performance for large-scale genome and multimodal biological models across a wide range of real-world applications, including therapeutics, diagnostics, synthetic biology, and biodefense.

This is a highly technical role at the intersection of AI systems, distributed computing, and model deployment. You will work closely with research, infrastructure, and external partners to ensure our models can be efficiently deployed, scaled, and integrated into production environments. Success in this role requires deep expertise in large language model inference, kernel optimization, GPU systems, and performance engineering.

You should be excited by questions such as: How do we reduce inference latency for 100B MoE models? How do we maximize throughput across heterogeneous hardware environments? How do we optimize custom kernels for emerging hybrid model architectures? How do we deploy foundation models reliably across cloud, on-premise, and highly regulated environments? How do we enable our partners to transform biological research and development through production-grade AI systems?

What You'll Do

• Drive end-to-end performance improvements. Identify and eliminate bottlenecks across the inference stack, from model execution and memory management to networking, scheduling, and hardware utilization.
• Develop high-performance inference primitives. Build and optimize GPU kernels, numerical operators, and serving infrastructure to maximize throughput, latency, and efficiency on modern accelerator platforms.
• Partner with external customers and collaborators. Work directly with pharmaceutical companies, biotech organizations, research institutions, and government partners to deploy models in production environments and solve challenging technical problems.
• Build scalable deployment infrastructure. Create systems for serving, monitoring, benchmarking, and operating foundation models reliably across cloud, enterprise, and secure environments.
• Collaborate with research and platform teams. Ensure new model architectures can be efficiently deployed at scale and help translate frontier AI research into real-world impact.

What We're Looking for

• Expertise in large-scale AI inference systems. Proven experience optimizing, deploying, and operating LLMs or other foundation models in production environments.
• Strong performance engineering and kernel development skills. Deep understanding of GPU architectures and experience with CUDA, Triton, or equivalent technologies for building high-performance numerical software.
• Systems-level thinking. Ability to diagnose and solve bottlenecks across the full stack, including model architectures, serving systems, networking, memory management, and distributed infrastructure.
• Hands-on builder. Strong software engineering fundamentals with proficiency in Python and modern ML frameworks such as PyTorch.
• Customer and deployment orientation. Experience working closely with users, customers, or cross-functional stakeholders to deliver production AI systems that solve real-world problems.
• Excellent technical communication. Ability to collaborate effectively across research, engineering, infrastructure, and scientific teams.

Nice to Have

• Experience with inference frameworks such as vLLM, TensorRT-LLM, SGLang, DeepSpeed, or similar systems.
• Contributions to open-source AI infrastructure, inference frameworks, compilers, or kernel libraries.
• Experience with distributed systems, cloud infrastructure, and large-scale GPU clusters.
• Familiarity with biological foundation models, computational biology, genomics, or scientific AI applications.
• Experience operating AI systems in regulated, secure, or mission-critical environments