Hands-on experience working with LLMs, with a strong focus on prompt engineering, building ML pipelines, and model integration
Understanding of quality evaluation metrics and practical experience with A/B testing for ML models
Ability to prioritize hypotheses, clearly justify the selection of specific models, methods or algorithms, and architect efficient engineering solutions
Experience delivering high-quality software, CI/CD pipelines, and end-to-end ownership of the development lifecycle from technical design to post-deployment monitoring
Expertise in Python and its ecosystem, as well as language- and framework-agnostic mindset to achieve project goals
Familiarity with various options for LLM providers, both commercial such as OpenAI, Anthropic, Cohere, etc, and open-source, such as Llama and Mistral
Familiarity with various open-source tools to build and evaluate RAG applications such as LangChain, LlamaIndex, Ragas, MLflow etc
Excellent communication skills and ability to explain complex technical concepts to a broad audience of stakeholders
B1 or higher English level for effective communication with an international team
Previous experience delivering business-critical ML/AI-powered applications
Experience with adapting, fine-tuning, and deploying open-source models (e.g., Llama, Mistral) in an on-premise or private cloud environment
Personal portfolio of hobby ML projects or contributions to open-source tools