Staff Inference Engineer — Production-Scale AI Platform

Designworks Talent LLC; Bellevue (KY); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Health insurance

401(k) plan with company match

Paid holidays

Job summary

Designworks Talent LLC is seeking a Staff Inference Engineer to build and operate the model-serving systems powering a next-generation AI inference platform. You will work on high-throughput, low-latency inference for production-scale APIs in a hybrid Bellevue, WA setting.

The role emphasizes optimizing GPU-backed workloads, collaborating with training and platform teams, and contributing to scalable, reliable production services across diverse model architectures.

Qualifications

• Experience building and operating production ML inference systems at scale.
• Understanding latency, throughput, memory usage, and cost trade-offs for large models.
• Experience designing reliable distributed systems or production infrastructure.
• Understanding GPU-backed AI workloads and scaling inference.
• Strong engineering fundamentals and ability to own complex problems.
• Comfortable in fast-moving environments where systems are built from the ground up.

Responsibilities

• Build and operate production-grade model-serving and inference systems for high-throughput AI workloads.
• Optimize inference infrastructure for token throughput, latency, scalability, and cost across models.
• Design systems to maximize GPU utilization with predictable performance.
• Improve scalability and operational maturity of inference platforms as demand grows.
• Collaborate with AI training, GPU performance, orchestration, and infra teams for smooth transitions from development to production serving.
• Develop monitoring, alerting, and operational practices for reliable inference services.
• Investigate and resolve performance, reliability, and capacity challenges across inference workloads.
• Contribute to architecture decisions and engineering standards as the platform evolves.

Skills

Production ML inference

Distributed systems

GPU computing

Performance optimization

LLM inference

Cloud infrastructure

Tools

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

Kubernetes

GPU scheduling

Job description

Designworks Talent LLC is seeking a Staff Inference Engineer to build and operate the model-serving systems powering a next-generation AI inference platform. You will work on high-throughput, low-latency inference for production-scale APIs in a hybrid Bellevue, WA setting.

The role emphasizes optimizing GPU-backed workloads, collaborating with training and platform teams, and contributing to scalable, reliable production services across diverse model architectures.