ML / AI Engineer

About the Role

We are looking for an experienced ML Engineer to join our team working on a data analysis system. iFORA is an intelligent big data analysis system (developed by ISIEZ HSE University) that analyzes over 850 million documents from a unique collection (scientific articles, patents, media) to support strategic decision-making.

Technology Stack

• Python, Linux
• PyTorch, Transformers
• LangChain / LangGraph
• vLLM, sglang, Triton Inference Server
• MLFlow
• S3-compatible storage
• Docker, Jupyter, VSCode

Responsibilities

• Development of multi-agent systems (MAS) for Deep Research tasks
• Creation of LLM agents using tool calling, planning, and reasoning
• Design and evolution of RAG architecture over a collection of 850+ million documents
• Development and maintenance of knowledge graphs for analytical and research scenarios
• LLM inference optimization (latency, throughput, batching, KV cache)
• Model preparation and optimization for production
• Development of reproducible ML pipelines and experiment infrastructure
• Deployment and operation of AI/ML services in production

Requirements

• 3+ years of experience implementing Machine Learning / AI projects
• Knowledge of pattern architecture and system design
• Strong proficiency in Python
• Experience developing LLM-based systems
• Experience building RAG systems or AI agents
• Experience deploying ML/AI services to production
• Understanding of ML pipeline architecture and engineering approach

Preferred Qualifications

• Experience with LangChain / LangGraph
• Experience developing multi-agent systems
• Experience implementing GraphRAG, AgenticRAG, Colbert
• Experience with inference optimization (vLLM, Triton, TensorRT, ONNX)
• Experience with model training or fine-tuning (LoRA, multi-GPU training)
• Experience with knowledge graphs or graph databases (Neo4j, ArangoDB, Neptune)
• Experience with ML experiment tracking (MLFlow, W&B, DVC)
• Experience with S3 storage
• Experience with multimodal models

Working Conditions & Benefits

• Participation in developing one of the largest scientific data analytics platforms
• Work with modern LLM and AI architectures
• Strong research and engineering team
• Flexible schedule (workday start between 8:00 and 11:00)
• Hybrid work format (remote work possible within Russia)
• Training and courses at HSE University, English language
• Access to HSE University library and educational resources
• Co-financed voluntary health insurance (DMS)
• Fitness club and theater loyalty programs
• Office on Myasnitskaya (Lubyanka / Turgenevskaya metro stations)