Member of Technical Staff, ML Engineer
Core
Build the inference APIs, batch and compute systems, and services that make the Omnii genome language model fast, reliable, and cheap at genome scale for scientists and partners.
Role type
Senior IC ML Infrastructure Engineer
Builds
Inference APIs, SDKs, documentation, and compute/orchestration layers for the Omnii model
Domain
AI/ML infrastructure for genomics and biological intelligence
Deliverable
production ML models
Required skills
Backend/distributed systems at production scale, Model-as-a-service (inference/serving), Asynchronous/batch job systems, Python, Typed languages, Containers, Infrastructure as code, Product judgment for APIs
Preferred skills
GPU inference internals (vLLM, TensorRT-LLM, Triton), Deploying to locked-down environments (enterprise VPC, on-prem, air-gapped), Genomics/computational biology, External API product development
Technologies
Python, vLLM, TensorRT-LLM, Triton
Responsibilities
Build real-time and batch inference APIs for genome-scale workloads; Design compute and orchestration layers with autoscaling and fault tolerance; Develop developer-facing products (APIs, SDKs, docs); Optimize cost and latency per inference; Package platform for on-prem and air-gapped environments; Collaborate with scientists and partners on API design
Seniority
Senior, hands-on IC