Staff AI Platform Engineer – Inference & RL Architect

Nscale; Seattle (WA); On-site; USD 220,000 - 293,000; Full time

Job summary

Nscale seeks a Staff AI Engineer (Specialized) to drive the architecture of its inference and reinforcement learning systems at the core of the AI services platform. You will own how models are served on Nscale’s GPU cloud, and how RL workloads run, exposing clean, high-performance interfaces to customers and internal teams.

You will define standards for model efficiency, API boundaries, and platform tooling, collaborating with multiple teams to raise engineering quality and ensure scalable,

Qualifications

• 8–12 years of engineering experience in production AI systems at scale.
• Ability to set technical direction for an AI systems domain.
• Deep expertise in production LLM inference and RL for LLMs.
• APIs/SDKs designed for engineers and external customers.

Responsibilities

• Set technical direction for inference serving architecture: routing, scheduling and batching.
• Lead RL and post-training systems: RLHF, reward modelling, and agentic RL.
• Define shared infrastructure for RL loops and data curation workflows.
• Design developer-facing APIs and SDKs that are clean and versioned.
• Coach engineers and align strategy with business direction.

Skills

Production AI systems

LLM inference

RL for LLMs

APIs & SDKs

Python & PyTorch

Transformer architectures

Cross-team influence

GPU/accelerator workloads

Tools

CUDA

Kubernetes

Triton

OpenAPI 3.x

Job description

Nscale seeks a Staff AI Engineer (Specialized) to drive the architecture of its inference and reinforcement learning systems at the core of the AI services platform. You will own how models are served on Nscale’s GPU cloud, and how RL workloads run, exposing clean, high-performance interfaces to customers and internal teams.

You will define standards for model efficiency, API boundaries, and platform tooling, collaborating with multiple teams to raise engineering quality and ensure scalable,