Member of Technical Staff, Inference
Core
Build and optimize systems for state-of-the-art inference performance of large-scale genome and multimodal biological models (e.g., Omnii-1) across therapeutics, diagnostics, synthetic biology, and biodefense.
Role type
Senior IC inference systems engineer (biological AI)
Builds
Production-grade AI inference systems for frontier biological models
Domain
AI systems, distributed computing, computational biology, genomics
Deliverable
production ML models
Required skills
Large-scale AI inference optimization, GPU kernel development, CUDA/Triton, Python, PyTorch, distributed systems, memory management, networking, serving infrastructure
Preferred skills
vLLM, TensorRT-LLM, SGLang, DeepSpeed, open-source AI infrastructure contributions, regulated/secure environment operations
Technologies
CUDA, Triton, PyTorch, vLLM, TensorRT-LLM, SGLang, DeepSpeed
Responsibilities
Identify and eliminate bottlenecks across the inference stack (execution, memory, networking, scheduling); Develop high-performance GPU kernels and serving infrastructure; Partner with external customers to deploy models in production; Build scalable deployment infrastructure for cloud, on-premise, and secure environments; Collaborate with research teams to translate model architectures into efficient deployments.