Principal AI Systems Architect - Inference & Post-Training

Greenhouse Software, Inc.; New York, San Francisco, Seattle (NY, CA, WA); On-site; USD 290,000 - 520,000; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

Flexible PTO

Parental leave

Retirement plan

Job summary

Nscale is seeking a Principal AI Engineer to lead the inference and post-training pillar of our AI systems engineering organization in the United States. You will shape the multi-year technical roadmap for serving models and post-training workloads, guiding 20–50+ engineers and defining API contracts and performance benchmarks.

You will own cost, latency, and quality trade-offs, drive cross-team collaboration, and mentor senior engineers while representing Nscale externally through open-source

Qualifications

• 10–15 years of engineering experience with a clear track record of pillar-level impact on production AI systems.
• 4+ years of hands-on work with LLMs in inference, GPU performance, evals, or post-training and RL, in production or research.
• Demonstrated ability to define multi-year technical strategy for complex, multi-team AI systems organizations.
• World-class depth in production LLM inference, GPU performance, evals, and/or post-training and RL infrastructure.

Responsibilities

• Define and own the multi-year technical roadmap for inference, evals, and post-training platform.
• Lead company-scale architectural initiatives across serving, GPU kernel and model efficiency, evals, and RL infrastructure.
• Establish engineering standards for API design, benchmarking, training stability norms, and performance testing.

Skills

LLM inference

GPU performance

Architecture design

Multi-team leadership

Tools

CUDA

Triton

TensorRT-LLM

Kubernetes

Job description

Nscale is seeking a Principal AI Engineer to lead the inference and post-training pillar of our AI systems engineering organization in the United States. You will shape the multi-year technical roadmap for serving models and post-training workloads, guiding 20–50+ engineers and defining API contracts and performance benchmarks.

You will own cost, latency, and quality trade-offs, drive cross-team collaboration, and mentor senior engineers while representing Nscale externally through open-source