Remote ML Platform Engineer for Scalable Inference

Bright Vision Technologies; Cranberry Township (Butler County); Remote; USD 100,000 - 160,000; Full time

Job summary

Bright Vision Technologies seeks an ML Platform Engineer to design, build, and operate high-performance inference platforms for large ML models.

The role emphasizes systems engineering for AI deployment, including routing, batching, caching, autoscaling, GPU utilization, and observability across model workloads.

The ideal candidate has shipped serving systems at scale and strong experience with LLM inference frameworks and cloud environments.

Qualifications

• Bachelor's or Master’s in CS or related field.
• 10+ years in distributed systems, infra, or ML platforms.
• Strong Python and systems language (Go/Rust/C++).
• Experience operating high-throughput, low-latency services in production.
• Hands-on with large model inference frameworks (vcLLM, TensorRT-LLM).
• Familiarity with Kubernetes, autoscaling, and cloud platforms.
• Observability: metrics, tracing, logging.
• Strong communication and incident response skills.

Responsibilities

• Design and operate model serving platforms for LLMs and vision/recommendation systems.
• Optimize inference with batching, caching, and multiplexing.
• Implement multi-tenant routing and QoS policies.
• Build autoscaling and capacity management for latency and cost.
• Tune GPU utilization and memory for LLM workloads.
• Integrate serving with API gateways and observability stacks.
• Develop deployment workflows with canary releases and rollback.
• Ensure high availability and durable reliability improvements.
• Collaborate with ML and product teams on releases.

Skills

Python

Go

Rust

Distributed systems

Low latency

Education

Bachelor's degree in CS

Tools

Kubernetes

TensorRT-LLM

vcLLM

Cloud platforms

Job description

Bright Vision Technologies seeks an ML Platform Engineer to design, build, and operate high-performance inference platforms for large ML models.

The role emphasizes systems engineering for AI deployment, including routing, batching, caching, autoscaling, GPU utilization, and observability across model workloads.

The ideal candidate has shipped serving systems at scale and strong experience with LLM inference frameworks and cloud environments.