Forward-Deployed AI Inference Engineer

Inferact; United States; Remote; USD 200,000 - 400,000; Full time

Benefits offered by this job

Health benefits

401(k) company match

Remote work within US

Job summary

Inferact is hiring a Forward Deployed Engineer to deploy, integrate, debug, and optimize vLLM-powered inference systems for real customers. You’ll work directly with customer teams across cloud, Kubernetes, GPU, networking, and model-serving environments, moving from architecture discussions to hands-on implementations.

You’ll handle production issues end-to-end, collaborating with core product and engineering to turn field insights into reusable features that improve time-to-value for customers.

Qualifications

• Bachelor’s degree or equivalent in CS/engineering/ML.
• Strong software engineering in Python/Go/TypeScript with production-grade integrations.
• Hands-on experience deploying ML systems, model serving, or cloud platforms.
• Ability to work directly with customer engineering teams and drive implementations.
• Strong debugging across app, runtime, infra, networking, and observability.
• Ability to reason about latency, throughput, batching, scaling, and cost in production.
• High ownership and technical communication to convert issues into reusable features.

Responsibilities

• Deploy, integrate, debug, and optimize vLLM-powered inference systems inside customer environments.
• Work with product/engineering to turn field learnings into reusable product capabilities.
• Collaborate across cloud, Kubernetes, GPU, networking, and model-serving stacks.
• Own production problems end-to-end and communicate clear status to customers.

Skills

Python

Go

TypeScript

Production-grade integrations

Customer collaboration

Systems debugging

Latency/throughput considerations

Ownership & technical communication

Education

Bachelor’s degree or equivalent in CS/Engineering/ML

Tools

vLLM / SGLang / TensorRT-LLM / TGI / Ray Serve / BentoML

NVIDIA GPUs / CUDA

Kubernetes / cloud platforms

Job description

Inferact is hiring a Forward Deployed Engineer to deploy, integrate, debug, and optimize vLLM-powered inference systems for real customers. You’ll work directly with customer teams across cloud, Kubernetes, GPU, networking, and model-serving environments, moving from architecture discussions to hands-on implementations.

You’ll handle production issues end-to-end, collaborating with core product and engineering to turn field insights into reusable features that improve time-to-value for customers.