Remote ML Systems Engineer: Scale AI Inference

Bright Vision Technologies; Flower Mound (TX); On-site; USD 145,000 - 165,000; Full time

Job summary

Bright Vision Technologies is seeking an ML Systems Engineer to design, build, and operate high-performance inference platforms for production ML models. This role emphasizes scalable systems engineering, request routing, batching, caching, autoscaling, and observability across model workloads.

The ideal candidate has distributed systems experience and ships serving systems at scale. The candidate should be proficient in Python and a systems language (Go, Rust, or C++), with deep knowledge of

Qualifications

• Six+ years in distributed systems, infrastructure, or ML platform engineering.
• Strong Python and a systems language (Go, Rust, or C++).
• Experience operating high-throughput, low-latency services in production.
• Hands-on with LLM inference frameworks like vLLM or TensorRT-LLM.
• Familiarity with GPUs, memory hierarchies, and accelerator utilization.
• Kubernetes, autoscaling, and modern cloud platforms knowledge.
• Observability stacks with metrics, tracing, and logging.
• Excellent communication and incident-response skills.

Responsibilities

• Design, build, and operate high-performance ML inference platforms.
• Focus on request routing, batching, caching, autoscaling, and observability.
• Balance latency, throughput, cost, and quality in ML serving.

Skills

Python

Go

Rust

C++

Distributed Systems

Low Latency

LLM frameworks

GPU Architecture

Kubernetes

Autoscaling

Cloud Platforms

Observability

Performance Engineering

Communication

Education

CS degree

Tools

vLLM

TensorRT-LLM

Job description

Bright Vision Technologies is seeking an ML Systems Engineer to design, build, and operate high-performance inference platforms for production ML models. This role emphasizes scalable systems engineering, request routing, batching, caching, autoscaling, and observability across model workloads.

The ideal candidate has distributed systems experience and ships serving systems at scale. The candidate should be proficient in Python and a systems language (Go, Rust, or C++), with deep knowledge of