Senior Artificial Intelligence/Machine Learning Engineer (4101)

Що робити

• LLM Pipeline Engineering: Build and optimize multi-pass generation pipelines using self-hosted open-weight LLMs (Llama 3.1, Mixtral) running on local GPU infrastructure
• NLI & Validation Development: Design and integrate NLI-based validation layers and automated confidence filtering to consistently meet the ≥92% factual precision threshold
• Context Assembly & RAG: Implement advanced RAG retrieval routines combining Neo4j graph traversal and Qdrant vector search for structured code context generation
• Prompt Optimization & Fine-Tuning: Develop, test, and benchmark domain-specific prompts and structured output templates for multi-level code summarization
• Inference Optimization: Tune model throughput, latency (p95 About us: