golang engineer for AI infrastructure

Claven AI is a Tashkent-based startup building a Sovereign AI Infrastructure & Orchestration Platform that turns bare-metal or managed GPU clusters into efficient, cloud-native AI clouds. The platform supports inference, model fine-tuning, and GPU workload management at scale, with a focus on data sovereignty for enterprise and government customers in regulated industries.

• Build and evolve core Go services that orchestrate AI/ML workloads on Kubernetes, including inference traffic routing, workload provisioning and reconciliation through the Kubernetes API, and lifecycle management;
• Write controllers, operators, admission webhooks, and custom resources using controller-runtime / kubebuilder, including GPU-aware scheduling and placement;
• Integrate and tune the model-serving stack for cost, latency, and throughput, including multi-GPU tensor-parallel serving and model artifact lifecycle management;
• Implement multi-tenancy, network policy, and workload isolation for data-sovereignty and air-gapped operating modes, including per-tenant isolation, quotas, and RBAC;
• Own the platform's API contracts and partner with frontend engineers on backend–UI integration points, including gateway and identity layers;
• Diagnose and resolve production issues across the stack while onboarding pilot customers;
• Take ownership of problems within the assigned area and work independently;
• Investigate unfamiliar systems with AI assistance and return with answers, prototypes, and opinions;
• Maintain curiosity and learning velocity.

• Strong production-grade Go experience building and operating real services;
• Deep Kubernetes knowledge, including the API and controller/reconciliation model;
• Experience operating Kubernetes clusters and debugging incidents;
• Strong Linux, networking, and systems fundamentals;
• Hands-on experience with infrastructure-as-code, observability tooling, and CI/CD pipelines;
• Ability to own API contracts, document decisions, and communicate clearly;
• Strong written English and clear, low-ego communication;
• 4+ Years in backend, platform, infrastructure, or SRE roles is a useful soft floor, not a hard gate;
• Nice to have: Kubernetes controllers, operators, admission webhooks, or custom resources; NVIDIA stack including CUDA, MIG, NCCL, or DCGM; GPU partitioning and virtualization including time-slicing or MPS; production LLM serving with vLLM, TGI, SGLang, or similar; multi-tenancy, network policy, or compliance work in regulated industries; Python; API gateway or identity/OIDC work; ML platforms, developer infrastructure, or internal PaaS-style products; usage-based metering and quota systems.

• Fully remote, globally;
• Working hours should overlap meaningfully with the team;
• Compensation is discussed during the hiring process and is competitive for the candidate's market;
• Ownership of a critical platform layer from day one;
• Direct work with the founders and a small AI-native engineering team;
• Real customer pipeline in regulated markets, including pilots.