Golang Developer

About Claven AI

Claven AI is a startup based in Tashkent focused on building a Sovereign AI Infrastructure & Orchestration Platform that transforms GPU clusters into efficient, cloud-native AI clouds. The platform facilitates running inference, fine-tuning models, and managing GPU workloads at scale, prioritizing data sovereignty for enterprise and government clients in regulated sectors like banking, finance, healthcare, defense, and academia. The company emphasizes high performance, cost efficiency, modern architecture, and streamlined integration for both large language models and traditional machine learning workloads.

Work Culture and Approach

As an AI-native team, Claven incorporates agentic AI tools like Claude Code into daily workflows to accelerate development. Team members are expected to actively use such AI assistants not just experimentally but as fundamental tools. When encountering unfamiliar systems such as GPU scheduling internals or model-serving engines, employees are encouraged to explore deeply using AI support and return with insights, prototypes, and recommendations. A culture of ownership, continuous curiosity, learning velocity, and proactive problem-solving is essential.

Key Responsibilities

• Develop and maintain core backend services using Go that orchestrate AI/ML workloads on Kubernetes clusters, including traffic routing, workload provisioning, and lifecycle management.
• Design and implement Kubernetes controllers, operators, admission webhooks, and custom resources focusing on GPU-aware scheduling and placement.
• Integrate and optimize the model-serving infrastructure to balance cost, latency, and throughput, including multi-GPU serving and managing model artifacts.
• Implement multi-tenancy, network policies, and workload isolation to support data sovereignty and air-gapped modes, managing per-tenant isolation, quotas, and role-based access control.
• Own and maintain API contracts exposed by the platform, working closely with frontend engineers on API boundaries, gateway, and identity layers.
• Assist in diagnosing and resolving production issues during pilot customer onboarding.

Qualifications and Experience

• Proven expertise in production-grade Go development with experience building and operating real backend services.
• Deep knowledge of Kubernetes APIs and controller reconciliation patterns, plus hands-on experience managing and debugging Kubernetes clusters.
• Strong fundamentals in Linux, networking, and system administration.
• Experience with infrastructure-as-code tools, observability solutions, and continuous integration/continuous deployment pipelines.
• Effective ownership of API design and clear, written communication skills in English.
• Generally, 4 or more years of experience in backend, platform infrastructure, or SRE roles, though strong skills may compensate for less.

Preferred but Not Required Skills

• Experience writing Kubernetes controllers, operators, admission webhooks, or custom resources using controller-runtime/kubebuilder.
• Familiarity with NVIDIA GPU stack including CUDA, MIG, NCCL, DCGM, or GPU virtualization techniques.
• Serving large language models in production environments such as vLLM, TGI, or similar.
• Expertise in multi-tenancy, network policy management, or compliance in regulated industries.
• Comfort with Python as some services are written in it.
• Knowledge of API gateway or identity management (OIDC).
• Background in machine learning platforms, developer tools, or PaaS solutions including usage-based metering and quota management systems.

Benefits and Work Environment

• Ownership of a vital platform component from the start.
• Direct collaboration with founders and a small AI-focused engineering team without bureaucratic hurdles or politics.
• Real customer engagements in regulated markets with live pilots rather than hypothetical projects.
• Fully remote position with global hiring; requires work hours that adequately overlap with the team.
• Compensation is competitive and tailored to the candidate's market and discussed during the hiring process.