Principal Engineer – Distributed Systems (GPU Edge + Inference) jobs in United States
cer-icon
Apply on Employer Site
company-logo

Elloe AI | Immune System for AI · 5 months ago

Principal Engineer – Distributed Systems (GPU Edge + Inference)

Elloe AI is a company that serves as the trust layer for AI, ensuring safety and compliance for institutions like hospitals and banks. They are seeking a Principal Engineer to lead their GPU-edge inference systems, focusing on global infrastructure that enhances AI performance and compliance.

Customer ServiceSaaSSoftware

Responsibilities

Design zone-routing that ensures <50ms SLA in 10+ regions
Build fallback orchestration to handle compliance-aware rollbacks
Maximize utilization across 100K+ GPUs via mesh & load prediction
Integrate compliance overlays with VaultChain and SHAP triggers
Ship `/vault/audit`, `/inference/predict`, `/compliance/log` endpoints
Trace every edge request across governance and model layers

Qualification

GPU Infra OpsGlobal Edge RoutingReal-time AI infrastructureCompliance observabilitySoft skills

Required

Senior systems engineer with GPU fleet experience (KubeRay, Istio, Envoy)
Operated real-time AI infra with 10M+ QPS loads
Comfortable with compliance observability and infra governance

Preferred

Timezone overlap with NY or EU preferred

Benefits

Top of market salary
Equity

Company

Elloe AI | Immune System for AI

twittertwittertwitter
company-logo
Elloe AI is the immune system for AI — the real-time compliance layer making GenAI safe to deploy across regulated industries.

Funding

Current Stage
Early Stage
Total Funding
$1M
Key Investors
Mad Ventures
2022-04-06Pre Seed· $1M
Company data provided by crunchbase