Member of Technical Staff, ML Engineer at radical-numerics

Department: R&D

Setup: On-site
Location: San Francisco, California
Level: not_specified
Posted: Jul 3, 2026

Description

Radical Numerics is hiring a Member of Technical Staff, ML Engineer to build and operate the inference APIs, batch and compute systems, SDKs, and developer-facing services for Omnii, a genome-scale language model. The role focuses on real-time and large-batch serving, GPU autoscaling, fault tolerance, observability, cost and latency optimization, and secure on-prem or air-gapped deployments, while working with scientists and partners to shape the API around real inference workloads.

Required Skills

Python
Distributed systems
GPU inference
vLLM
TensorRT-LLM
Triton
Infrastructure as code
Observability

Additional Information

Required Previous Experiences: Built and operated backend or distributed systems at production scale, owning reliability
Shipped a model-as-a-service product with inference, serving, and throughput focus
Built asynchronous or batch job systems at scale, including genome-scale workloads
Wrote production code in Python and a typed language, with containers and infrastructure as code
Developed product judgment for API design and developer experience
Operated well with ambiguity and sought ownership in an early technical role
Preferred Qualifications: GPU inference internals with vLLM, TensorRT-LLM, or Triton and performance tuning
Deploying software into enterprise VPC, on-premises, or air-gapped environments
Familiarity with genomics or computational biology
Experience building an external API product from the first endpoint