Forward-Deployed AI Systems Engineer

Inferact; San Francisco (CA); Remote; USD 200,000 - 400,000; Full time

Benefits offered by this job

Visa sponsorship available

Health, dental, vision benefits

401(k) company match

Job summary

Inferact is seeking a Forward Deployed Engineer to bring our vLLM-powered inference to real customer environments. You will deploy, integrate, debug, and optimize systems across cloud, Kubernetes, GPU, and networking, moving from architecture discussions to concrete implementations.

You will work directly with customer teams, own difficult production problems end‑to‑end, and collaborate with product and engineering to translate field learnings into reusable capabilities.

Qualifications

• Bachelor's degree in CS/engineering or equivalent.
• Strong production-grade software engineering in Python/Go/TypeScript.
• Hands-on experience deploying ML systems and AI infra in production.
• Ability to collaborate with customer engineering teams end-to-end.
• Excellent debugging across systems, networks, and runtimes.
• Ability to reason about latency, throughput, and cost tradeoffs.
• Strong ownership and clear technical communication.

Responsibilities

• Deploy and integrate vLLM-powered inference in customer environments.
• Diagnose and resolve production issues end-to-end.
• Work with product and engineering teams to turn field learnings into features.
• Optimize performance across cloud, Kubernetes, GPUs, and networking.

Skills

Python

Go

TypeScript

Production deployments

ML infrastructure

Debugging

Latency & throughput

Customer collaboration

High ownership

Education

Bachelor's degree or equivalent

Tools

CUDA/ROCm

Job description

Inferact is seeking a Forward Deployed Engineer to bring our vLLM-powered inference to real customer environments. You will deploy, integrate, debug, and optimize systems across cloud, Kubernetes, GPU, and networking, moving from architecture discussions to concrete implementations.

You will work directly with customer teams, own difficult production problems end‑to‑end, and collaborate with product and engineering to translate field learnings into reusable capabilities.