Job description

KoiReader Technologies is seeking a skilled Lead Infrastructure Engineer to own the architecture of our cutting-edge Bare Metal and Edge Computing platform. You will play a pivotal role in orchestrating our AI/GenAI solutions directly on on-premise edge servers, ensuring high availability and seamless delivery for Fortune 500 clients in environments where the public cloud is often not an option.

Roles & Responsibilities

Edge Infrastructure Management: Design, deploy, and maintain lightweight Kubernetes infrastructure (RKE2, K3s) directly on bare-metal servers, ensuring robustness in constrained environments.

GitOps & Automation: Architect and maintain robust CI/CD pipelines using GitLab, adhering to GitOps principles to automate application delivery to distributed edge nodes.

Release Engineering: Package, configure, and automate complex AI product releases using Helm charts across Development, Test, and Production environments.

Observability: Integrate and manage the full Grafana Observability Stack (Prometheus, Loki, Grafana, Tempo, and Promtail) for deep monitoring of hardware health, application performance, and cluster logs.

System Optimization: Monitor node and kernel-level metrics to drive cost optimization, performance tuning, and capacity planning for high-compute AI workloads.

Client Collaboration: Lead technical discussions with client IT teams to facilitate secure deployment and support of our products within their on-premise data centers.

Skills Required

Edge Orchestration: Deep expertise in Kubernetes, specifically with RKE2 or K3s setup from scratch. You must understand how to build a cluster without managed cloud services.

Bare Metal Mastery: Hands-on experience configuring and managing physical servers (Linux/Ubuntu/RHEL). You should be comfortable with PXE booting, file systems, and Linux kernel tuning.

Physical Networking: Strong understanding of Layer 2/Layer 3 networking (BGP, ARP), Load Balancing on bare metal (MetalLB, Kube-VIP), and firewalls.

Scripting & Automation: Proficiency in Bash and Python for automating system administration tasks and hardware provisioning.

Monitoring: Expert-level knowledge of the Grafana/Prometheus ecosystem, specifically for monitoring physical resources.

Communication: Excellent communication skills paired with a relentless drive to master emerging edge architectures.

Brownie Points (Nice to Have)

Hardware Acceleration: Experience managing NVIDIA GPUs, configuring CUDA drivers, and using the NVIDIA Container Toolkit.

Security: Knowledge of System Security (SAST/DAST), Air-Gapped deployments, and OS hardening (CIS Benchmarks).

Storage: Experience with distributed block storage for edge (e.g., Longhorn, Rook/Ceph, or Local Path Provisioning).

What We Offer

Culture: A meritocracy-driven, candid startup culture that values autonomy.

Tech: Work with the latest GenAI and Computer Vision technologies as an NVIDIA partner.

Impact: Architect high-availability infrastructure that orchestrates GenAI and Computer Vision workloads from the Edge to the Cloud, powering major global supply chains.

Someone shared one job with you. ASAI keeps finding the rest.

Scored, not searched. Every role ranked against your actual profile.

Alerts as often as hourly. Reach new roles while the pile is still small.

Skill gaps, spelled out. See exactly which requirements you don't meet yet.

Verified jobs, only. Say no to ghost jobs. Your time deserves respect.

Someone shared one job with you. ASAI keeps finding the rest.