Artificial Intelligence / Machine Learning Engineer (4100)

Ciklum

Що робити

AI Pipeline Development: Implement and maintain multi-pass LLM generation workflows using self-hosted open-weight models (Llama 3.1, Mixtral)
RAG Retrieval Integration: Connect vector search routines (Qdrant) and graph queries (Neo4j) into unified prompt context builders
Evaluation Pipeline Support: Integrate automated NLI checking scripts to filter low-confidence generations and verify factual precision
Prompt Engineering & Templating: Construct, benchmark, and refine domain-specific prompts to output structured Markdown assets
Cross-Functional Collaboration: Partner with Data Engineers on schema ingestion and work with QA to validate AI-generated output quality against code baselines

Professional Experience: 3+ years in commercial software development or data science, with 1.5+ years building and deploying practical LLM/AI applications
Core Technical Stack: High proficiency in Python, clean code principles, REST APIs, and asynchronous programming
Practical AI/RAG Exposure: Demonstrated working knowledge of RAG architectures, prompt design, and vector databases (Qdrant/OpenSearch)
Model Execution Understanding: Familiarity with self-hosted open-weight LLM workflows, token management, and inference engines (vLLM, TGI)
Engineering Best Practices: Hands-on experience with Git, Docker containerization, unit testing, and CI/CD pipelines

Знайдено через trackr.help/jobs · Канал: @trackrhelp · Бот для персональних сповіщень: @trackrhelpBot