Member of Technical Staff, ML Engineer

About the role

The Member of Technical Staff, ML Engineer owns the layer between the models and the users, building APIs, batch and compute systems that make inference fast, reliable, and cost‑effective at genome scale. You will work closely with scientists, partners, and product teams to deliver the next‑generation genome language model, Omnii.

Key responsibilities

• Build real‑time and large‑batch inference APIs for genome‑scale workloads, optimizing latency, throughput and cost.
• Design and operate the compute orchestration layer, including job queues, autoscaling GPU inference, fault tolerance, and observability to meet SLAs.
• Develop the developer‑facing product: API surface, SDKs, and documentation for external teams.
• Reduce inference cost and latency, package the platform for on‑premise and air‑gapped partner environments.

Required profile

• Experience building and operating backend or distributed systems at production scale with a focus on reliability.
• Proven track record shipping a model‑as‑a‑service used by other teams.
• Comfort with ambiguity and ownership of early‑stage technical roles.

Required skills

• Production‑grade Python programming.
• Proficiency in at least one typed language (e.g., Go, Java, C++).
• Containerization and infrastructure‑as‑code experience.
• Knowledge of GPU inference frameworks such as vLLM, TensorRT‑LLM, or Triton.