AI Systems Platform Engineer – Real-Time Threat Detection

Menlo Security; United Kingdom; Remote; GBP 110,000 - 170,000; Full time

Job summary

Menlo Security is seeking an AI Systems Infrastructure Engineer (IC4) to lead the platform and backend architecture powering real-time security detection services. You will build and scale low-latency serving infrastructure for SLMs and PI engines across GPU and cloud clusters.

You will own production backend services, GPU replica scaling, guardrails, and automated evaluation pipelines to ensure reliable, high-performance detection at scale.

Qualifications

• 5+ years of software engineering with distributed backend systems.
• Proven model serving and inference optimization experience.
• Strong Python, Go, or C++ programming skills.
• Hands-on Kubernetes and container orchestration expertise.
• Experience with CI/CD, MLOps/LLMops, and cloud (AWS/GCP).

Responsibilities

• Architect, build, and optimize production serving pipelines for SLMs and ML models.
• Own GPU cluster replicas and minimize cold-start times.
• Develop monitoring, guardrails, and automated evaluation pipelines.

Skills

Distributed backend

Model serving

Python

Go

C++

Kubernetes

CI/CD

MLOps

Cloud AWS/GCP

Tools

TensorRT

ONNX Runtime

Triton Inference Server

GPU Scheduling

Job description

Menlo Security is seeking an AI Systems Infrastructure Engineer (IC4) to lead the platform and backend architecture powering real-time security detection services. You will build and scale low-latency serving infrastructure for SLMs and PI engines across GPU and cloud clusters.

You will own production backend services, GPU replica scaling, guardrails, and automated evaluation pipelines to ensure reliable, high-performance detection at scale.