Remote AI Backend Engineer: Production Inference

Procom; United States; Remote; USD 110,000 - 170,000; Full time

Job summary

Procom is seeking a Backend Engineer for a permanent, remote role based in Austin, Texas. You will own the inference and orchestration layer powering AI interactions and build production systems that expose fast, observable APIs across clients.

Responsibilities include designing inference pipelines, managing monitoring and incident response, and optimizing latency across caching, batching, and streaming. Strong backend fundamentals and experience with high-throughput services are essential.

Qualifications

• Experience building production-grade backend services.
• Ability to operate high-throughput, low-latency systems.
• Familiarity with AI inference patterns (LLMs, embeddings).
• Bias toward shipping and learning from production metrics.

Responsibilities

• Own inference and orchestration layers powering AI features.
• Design pipelines, boundaries, and production readiness.
• Monitor, log, alert, and respond to incidents.
• Optimize latency across inference, caching, batching, and streaming.

Skills

Backend fundamentals

High-throughput services

AI inference patterns

Distributed systems debugging

Shipping in production

Tools

Kubernetes

Docker

Python

NodeJs

PyTorch

Open-source LLMs

SQL

NoSQL

Job description

Procom is seeking a Backend Engineer for a permanent, remote role based in Austin, Texas. You will own the inference and orchestration layer powering AI interactions and build production systems that expose fast, observable APIs across clients.

Responsibilities include designing inference pipelines, managing monitoring and incident response, and optimizing latency across caching, batching, and streaming. Strong backend fundamentals and experience with high-throughput services are essential.