Co-founder of a startup (for a share in the project without a salary at the start)

We are creating our own AI platform that allows companies to build AI agents and web applications. Our platform is a low-code + AI-coding + proprietary decentralized GPU network in one product. Companies get everything they need to develop and launch AI agents.

Where we are The team is formed, the product architecture is worked out. The low-code platform is about 90% ready, pilot and commercial projects have already been implemented on it. Now we need improvements in AI-coding. We are looking for an ML/LLM engineer who will be responsible for the architecture of the platform's AI infrastructure and will play an important role in the development of the entire project.

What you will be doing – Deployment and operation of LLMs on distributed servers – Participation in building decentralized computation pools – Integration of the LLM layer with the low-code platform – Optimization of inference performance and cost – Monitoring, logging, alerting, fault tolerance

What is important in a candidate – Experience in operating ML/LLM services in production (inference is more important than training) – Proficient Linux, understanding of the GPU stack (NVIDIA drivers, CUDA) – Docker, Python – Understanding of inference performance: batching, parallelism, queues, backpressure – Monitoring (Prometheus / Grafana or similar) – Understanding of RAG and vector search infrastructure Experience with LLM inference engines and optimizations (quantization, KV-cache, speculative decoding), as well as working with on-prem or closed infrastructure environments, will be a plus.

Conditions We are developing our own technological project, so at the current stage, the work is without a salary. Salary will appear after the platform launch and the arrival of the first clients. In return, we offer a share in the project – at the co-founder level. Employment: 15–20 hours per week, fully remote. The format is compatible with full-time employment.

Who it suits Those who want to build a technological product, not just work for hire. If you are interested in AI infrastructure, LLM platforms, and distributed computing, and you want your technical contribution to become part of a scalable product, let's talk in more detail.

For all questions, please write to @sumotori_