Senior Inference Platform Engineer

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

Benefits offered by this job

Hybrid work model

Office Bellevue

Competitive compensation

Job summary

Designworks Talent is seeking an Inference Engineer to build and operate production-grade model-serving and inference systems in a hybrid Bellevue, WA setting. You’ll work across distributed systems, GPU optimization, and production AI infrastructure to deliver high-throughput, low-latency inference.

Join a fast-moving team shaping next-gen AI platforms with scalable tooling, monitoring, and reliability practices, collaborating with AI training and platform teams.

Qualifications

• Experience building and operating production ML inference or model-serving systems at scale.
• Understanding of latency, throughput, memory utilization, and cost efficiency in serving large AI models.
• Experience designing reliable distributed systems or production infrastructure.
• Familiarity with GPU-backed AI workloads and scaling inference systems.

Responsibilities

• Build and operate production-grade model-serving and inference systems for high-throughput AI workloads.
• Optimize inference infrastructure for latency, throughput, and cost efficiency across workloads.
• Design systems to maximize GPU utilization with predictable performance and reliability.
• Improve scalability and maturity of inference platforms as demand grows.
• Collaborate with AI training and platform teams for smooth transitions from development to production.
• Develop monitoring and alerting to maintain reliable inference services.
• Investigate performance, reliability, and capacity challenges in inference workloads.

Skills

Production ML inference

Distributed systems

GPU workloads understanding

Problem ownership

Fast-moving environment

Tools

vLLM

TensorRT-LLM

Triton Inference Server

Kubernetes

Cloud infrastructure

Job description

Designworks Talent is seeking an Inference Engineer to build and operate production-grade model-serving and inference systems in a hybrid Bellevue, WA setting. You’ll work across distributed systems, GPU optimization, and production AI infrastructure to deliver high-throughput, low-latency inference.

Join a fast-moving team shaping next-gen AI platforms with scalable tooling, monitoring, and reliability practices, collaborating with AI training and platform teams.