Python Infrastructure Engineer (AI/LLM Platform)

• 💫 Fully remote, B2B contract

• 💫 Preferred locations: Georgia, Poland, Kazakhstan, Moldova, Serbia (we are also open to considering other locations)

• ⚠️No Russia, Belarus

SiriusOne (siriusone.com) is a software development company specializing in AI, CyberSecurity, and VR/AR domains. We collaborate closely with clients to create digital products that enhance business performance and provide a competitive edge. Our end-to-end development services ensure reliable, scalable, and high-impact solutions, leveraging cutting-edge technologies to drive innovation.

We are currently looking for a Senior Python Infrastructure Engineer (AI/LLM Platform) to join a project for one of our key clients a leading company focused on developing advanced AI models and large-scale intelligent systems. We expect the candidate to have a startup mindset – move fast, ready for pivoting, while building a reliable infrastructure.

Responsibilities:

• Develop ML infrastructure (backend for LLM inference, compute and code execute services);

• Implement new tools for our internal clients;

• Maintain the platform;

• Develop technical documentation;

• Gather requirements from our internal ML teams and offer optimal solution balancing different use cases;

• Be the part highly skilled MLOps engineers;

• Collaborate with users of LLM models Solution Engineers, ML Engineers to provide them with the best ml services and tools

Requirements:

• 5+ years experience as Software Engineer (primarily Python);

• Experience in infrastructure or backend development;

• Experience with C/C++: memory management and debugging, understanding of build systems (CMake/Make), ability to work with low-level code;

• Interest in working on internal infrastructure and MLOps;

• Ability to design solutions and maintain ML infrastructure;

• English language B2 or higher.

Nice to have:

• Understanding of instruments and practices for LLM training and inferencing;

• Experience with ML infrastructure;

• Familiar with popular DevOps tools: Kubernetes, Docker, Terraform;

• Knowledge of how to work with Spark (Databricks);

• Experience in working with Airflow (or there's ETL orchestration tools) and DBT;

• Experience integrating Python services with C/C++ modules is a plus;

• Familiarity with Java or other JVM languages is a plus