at Selectel for the development of the AI services platform: implementation of new features, working with AI/LLM model infrastructure, GPUs, and Kubernetes, platform support and optimization.
Tasks:
- Development of the platform and services: implementation of new features, improvement of existing components, creation of internal tools for working with AI services
- Development and evolution of technical solutions: independent implementation of changes, preparation of technical specifications for related teams, participation in platform architecture design, selection and implementation of new technical solutions
- Platform support and operation: ensuring stable service operation, monitoring status and performance analysis
- Working with AI model infrastructure: support for model deployment and serving services, GPU infrastructure development
- Optimization of model and computing resource performance: configuring request routing and fault tolerance, supporting the platform's multi-model architecture
- Interaction with internal users: studying platform usage experience, collecting and analyzing feedback
- Improving user experience with the service, assisting teams with connection and integration
- Preparation and maintenance of technical documentation: maintaining user documentation, describing processes, limitations, and recommendations
Requirements:
- Experience with Kubernetes in industrial operation and with AI/LLM infrastructure
- Experience with GPU infrastructure and NVIDIA stack
- Experience with vLLM / SGLang
- Experience with OpenAI-compatible APIs
- Experience with network infrastructure and monitoring systems
- Experience developing internal tools in Go or Python
- Ability to independently support and develop the entire service
Conditions:
- Experience: 1–3 years
- Full-time employment
- Schedule: 5/2
- Work format: remote or hybrid
Skills:
- Kubernetes
- AI/LLM
- GPU
- NVIDIA stack
- vLLM
- SGLang
- OpenAI API
- Go
- Python
- Monitoring
