AI Senior Engineer

O projekcie: The AI Senior Engineer is a core technical contributor responsible for the end-to-end development of Generative AI applications. At this level (6–8 years), we expect a professional who can independently navigate the complexities of LLM integration, RAG pipeline construction, and production-grade deployments. You will be the primary builder of intelligent agents and document intelligence tools, ensuring they are scalable, accurate, and secure. - Fully remote work model - Professional training programs – including Udemy and other development plans Wymagania: - Extensive Experience: 6–8 years of professional software engineering experience, with at least 2+ years dedicated exclusively to Generative AI and LLM implementation. - Advanced Python: Mastery of Python for AI/ML, including experience with asynchronous programming and high-performance web frameworks (FastAPI, Flask). - LLM Expertise: Deep hands-on experience with Google Gemini (Pro/Ultra/Flash) and a solid understanding of token management and prompt engineering techniques. - Framework Mastery: Proficiency in LangChain or LlamaIndex for building complex chains and agentic workflows. - Database Knowledge: Proven experience with Vector Databases (Pinecone, Weaviate, FAISS, or Chroma) including indexing, metadata filtering, and hybrid search. - Cloud & DevOps: Strong hands-on experience with Docker for containerization and basic orchestration within Google Cloud Platform (GCP). - Evaluation Metrics: Experience using RAGAS or similar frameworks for hallucination detection and model benchmarking. - Software Excellence: Strong understanding of CI/CD pipelines, Git-flow, and automated testing (Pytest). - Communication: Professional English (C1 level) with the ability to participate in deep technical discussions with global clients. - Agile Mindset: Deep familiarity with Agile/Scrum methodologies and Jira for task management. Codzienne zadania: - GenAI Development: Design and implement robust applications using Google Gemini, OpenAI, and open-source models for use cases like chatbots and copilots. - Orchestration: Build and maintain scalable pipelines using LangChain and LlamaIndex, focusing on multi-step workflows. - RAG Implementation: Construct end-to-end RAG pipelines that integrate enterprise data sources (PDFs, APIs, databases) while optimizing for high relevance and low hallucination. - Vector Management: Manage vector stores (Pinecone, Weaviate, FAISS) and design efficient embedding strategies and similarity search mechanisms. - Service Integration: Develop and expose AI microservices via REST/GraphQL APIs, ensuring they are ready for enterprise-wide consumption. - Performance Monitoring: Implement RAGAS frameworks to evaluate model precision, recall, and latency.