Remote ML Infrastructure Engineer: Scalable Inference

Bright Vision Technologies; Artesia, Cerritos (CA, CA); Remote; USD 105,000 - 143,000; Full time

Job summary

Bright Vision Technologies is hiring a Machine Learning Infrastructure Engineer to design, build, and operate high-performance inference platforms for large ML models. The role centers on systems engineering for AI deployment, including request routing, batching, caching, autoscaling, and end-to-end observability.

The ideal candidate has distributed systems expertise, ships serving systems at scale, and can balance latency, throughput, cost, and quality across diverse model workloads.

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.
• Strong proficiency in Python and a systems language such as 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

Distributed systems

Performance engineering

Incident response

Communication

Observability

Capacity planning

Latency optimization

Education

Bachelor’s or Master’s in CS

Tools

Python

Go

Rust

C++

Kubernetes

Autoscaling

Cloud platforms

vLLM

TensorRT-LLM

Job description

Bright Vision Technologies is hiring a Machine Learning Infrastructure Engineer to design, build, and operate high-performance inference platforms for large ML models. The role centers on systems engineering for AI deployment, including request routing, batching, caching, autoscaling, and end-to-end observability.

The ideal candidate has distributed systems expertise, ships serving systems at scale, and can balance latency, throughput, cost, and quality across diverse model workloads.