AI Systems Infrastructure Engineer — Real-Time SLM & GPU Scale

Menlo Security Inc.; Bracknell; Presencial; GBP 90.000 - 130.000; Tempo integral

Benefícios oferecidos por esta vaga

--

Resumo da vaga

Menlo Security is seeking an AI Systems Infrastructure Engineer to design and scale real-time security inference platforms. You will lead low-latency pipelines for SLMs, fine-tune GPU clusters, and implement automated evaluation and CI/CD for robust backend services.

You’ll collaborate with ML researchers while delivering production-grade microservices, guardrails, and scalable infrastructure across cloud clusters. Strong coding and Kubernetes expertise are essential.

Qualificações

• 5+ years building distributed backend systems.
• Proven experience with model serving and inference optimization.
• Strong programming in Python, Go, or C++.
• Hands-on with Kubernetes, container orchestration, GPU scheduling.
• Experience in cloud infra (AWS/GCP) and CI/CD.

Responsabilidades

• Architect, build, and optimize production serving pipelines for SLMs and traditional ML models.
• Own and scale backend microservices delivering real-time threat detection.
• Build consumption-based monitoring, tenant rate-limiting, and runtime guardrail infrastructure.
• Manage and optimize GPU cluster replicas (Kubernetes / Pod infrastructure) to minimize cold-start times and manage costs.
• Build CI/CD, automated evaluation, retraining pipelines, and model QA gates.
• Refactor service boundaries, auth flows, and backend DB configurations.

Conhecimentos

Distributed backend systems

Model serving

Python/Go/C++

Kubernetes

CI/CD

MLOps/LLMops

Ferramentas

TensorRT

ONNX Runtime

Triton Inference Server

Descrição da vaga

Menlo Security is seeking an AI Systems Infrastructure Engineer to design and scale real-time security inference platforms. You will lead low-latency pipelines for SLMs, fine-tune GPU clusters, and implement automated evaluation and CI/CD for robust backend services.

You’ll collaborate with ML researchers while delivering production-grade microservices, guardrails, and scalable infrastructure across cloud clusters. Strong coding and Kubernetes expertise are essential.