Remote Model Serving Engineer — High-Performance AI

Bright Vision Technologies; Novi (MI); On-site; USD 74,000 - 98,000; Full time

Job summary

Bright Vision Technologies is seeking a Model Serving Engineer to design, build, and operate high-performance, highly reliable inference platforms for serving large machine learning models in production.

The role focuses on the systems engineering side of AI deployment, including request routing, batching, caching, autoscaling, GPU utilization, and end-to-end observability across diverse model workloads. The ideal candidate brings strong distributed systems and performance engineering expertise.

Qualifications

• Bachelor’s or Master’s degree in Computer Science or a related field.
• Six or more years of experience in distributed systems, infrastructure, or ML platform engineering.
• Proficiency in Python and a systems language (Go, Rust, or C++).
• Deep experience operating high-throughput, low-latency services in production.
• Hands-on experience with LLM or large model inference frameworks such as vLLM or TensorRT-LLM.
• Strong understanding of GPU architecture, memory hierarchies, and accelerator utilization.
• Familiarity with Kubernetes, autoscaling, and modern cloud platforms.
• Experience with observability stacks including metrics, tracing, and structured logging.
• Solid grounding in performance engineering and capacity planning.
• Strong communication and incident response skills.

Skills

Python

Go

Rust

C++

Distributed systems

Performance engineering

Observability

Incident response

GPU utilization

Education

Bachelor’s or Master’s degree in Computer Science or a related field

Tools

Kubernetes

Autoscaling

Cloud platforms

Job description

Bright Vision Technologies is seeking a Model Serving Engineer to design, build, and operate high-performance, highly reliable inference platforms for serving large machine learning models in production.

The role focuses on the systems engineering side of AI deployment, including request routing, batching, caching, autoscaling, GPU utilization, and end-to-end observability across diverse model workloads. The ideal candidate brings strong distributed systems and performance engineering expertise.