C

Senior Backend Engineer - AI Infrastructure & Orchestration Platform

claven β€’ Serbia
Remote
Apply
AI Summary

Design and develop a scalable AI infrastructure and orchestration platform for enterprise and government customers. Develop backend services and Kubernetes machinery to turn a GPU cluster into a multi-tenant AI platform. Collaborate with a small, AI-native engineering team to build a critical layer of the platform.

Key Highlights
Design and develop a scalable AI infrastructure and orchestration platform
Develop backend services and Kubernetes machinery
Collaborate with a small, AI-native engineering team
Key Responsibilities
Build and evolve core Go services that orchestrate AI/ML workloads on Kubernetes
Write controllers, operators, admission webhooks, and custom resources
Implement multi-tenancy, network policy, and workload isolation
Technical Skills Required
Go Kubernetes Linux
Benefits & Perks
Ownership of a critical layer of the platform from day one
Direct work with the founders and a small, AI-native engineering team
Fully remote, globally
Nice to Have
Writing Kubernetes controllers, operators, admission webhooks, or custom resources
Hands-on with the NVIDIA stack (CUDA, MIG, NCCL, DCGM) or GPU partitioning and virtualization
Serving LLMs in production

Job Description


Claven AI (https://claven.ai/) is a Tashkent based startup building a Sovereign AI Infrastructure & Orchestration Platform β€” a system that turns bare-metal or managed GPU clusters into cloud-native, efficient, and profitable AI clouds. We make it easy to run inference, fine-tune models, and manage GPU workloads at scale, with a strong focus on data sovereignty for all customers in Uzbekistan and around the globe. We target enterprise and government customers in regulated industries β€” banking, finance, healthcare, defense, academia β€” and already have pilot projects in the pipeline. Our edge is performance, cost efficiency, modern architecture, and a simplified integration experience across both LLM and traditional ML workloads. We work in a transparent, low-ego, technology-first way, with a culture of hard work, camaraderie, and customer obsession.


How We Work

We are an AI-native team. We use Claude Code daily, alongside other agentic AI tools and workflows to ship faster. This is not a perk, it is how the work happens here. If you join us, we expect that:

  • You actively use Claude Code, Cursor, or similar agentic AI in your daily workflow β€” not as a curiosity, but as your default way of working.
  • When handed an unfamiliar system (GPU scheduling internals, a model-serving engine, a new operator or controller), you go deep on it with AI as your accelerator and come back with answers, prototypes, and opinions.
  • You take ownership. You don't wait to be told what to do once a problem is in your lane.
  • You maintain curiosity and learning velocity.


What You'll Own

You will own the backend services and Kubernetes machinery that turn a GPU cluster into a multi-tenant AI platform. This is real distributed-systems and Kubernetes-API work, not CRUD.

Specifically:

  • Build and evolve our core Go services that orchestrate AI/ML workloads on Kubernetes β€” routing inference traffic, provisioning and reconciling workloads through the Kubernetes API, and managing their lifecycle.
  • Write controllers, operators, admission webhooks, and custom resources (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 the model artifact lifecycle.
  • Implement multi-tenancy, network policy, and workload isolation in support of our data-sovereignty and air-gapped operating modes β€” per-tenant isolation, quotas, and RBAC.
  • Own the API contracts the platform exposes, and partner with our frontend engineers on the seams where the backend meets the UI, including the gateway and identity layers.
  • Help diagnose and resolve production issues across the stack as we onboard pilot customers.


What We're Looking For

We care more about what you can actually do than how many years it took you to get there.

The bar is:

  • Strong, production-grade Go β€” you've built and operated real services, not just scripts.
  • Real Kubernetes depth: you understand the API and controller/reconciliation model, and you've operated clusters β€” debugging incidents, not just kubectl apply-ing to a cluster someone else runs.
  • Strong Linux, networking, and systems fundamentals.
  • Hands-on with infrastructure-as-code, observability tooling, and CI/CD pipelines.
  • Comfortable owning an API contract and the boundary it sits on; you write things down 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.


Bonus Points

None of these are required. They will accelerate your ramp-up, and we are happy to hire someone with strong fundamentals and zero GPU experience who is excited to learn.

  • Writing Kubernetes controllers, operators, admission webhooks, or custom resources (controller-runtime / kubebuilder).
  • Hands-on with the NVIDIA stack (CUDA, MIG, NCCL, DCGM) or GPU partitioning and virtualization (MIG, time-slicing, MPS).
  • Serving LLMs in production (vLLM, TGI, SGLang, or similar).
  • Multi-tenancy, network policy, or compliance work in regulated industries.
  • Python β€” some of our services are Python; comfort crossing over helps.
  • API-gateway or identity/OIDC work.
  • Background in ML platforms, developer infrastructure, or internal PaaS-style products; familiarity with usage-based metering and quota systems.


What You Get

  • Ownership of a critical layer of the platform from day one.
  • Direct work with the founders and a small, AI-native engineering team β€” no bureaucracy, no political layers.
  • A real customer pipeline in regulated markets β€” pilots, not vaporware.
  • Fully remote, globally. We hire for talent and attitude. Working hours should overlap meaningfully with the team.
  • Compensation is discussed during the hiring process and is competitive for the candidate's market.

Similar Jobs

Explore other opportunities that match your interests

Visa Sponsorship Relocation Remote
Job Type Other
Experience Level Entry level

cognition commons

Serbia

Senior SEM Specialist / Team Lead

Programming
β€’
1w ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Entry level

roosevelt marketing outstaffin...

Serbia

Senior Kernel Developer - KernelCare Team

Programming
β€’
1w ago

Premium Job

Sign up is free! Login or Sign up to view full details.

β€’β€’β€’β€’β€’β€’ β€’β€’β€’β€’β€’β€’ β€’β€’β€’β€’β€’β€’
Job Type β€’β€’β€’β€’β€’β€’
Experience Level β€’β€’β€’β€’β€’β€’

CloudLinux

Serbia

Subscribe our newsletter

New Things Will Always Update Regularly