Lead Developer

Senior Machine Intelligence Interface Engineer Negotiable Georgia Tbilisi Full Remote Work experience 5 years 5 months Last work experience VkusVill ML Engineer 5 years 5 months Contacts About About AI Engineer specializing in production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, autonomous AI agents, and classic ML/NLP production pipelines. Proven track record of scaling high-load AI architectures in cloud environments, orchestrating microservices, and driving measurable business efficiency. Affiliate experience No data available Work experience 5 years 5 months May 2021 - September 2026 ( 5 years 5 months ) VkusVill ML Engineer • Support Ticket Intent Classification & Routing: Deployed an 8-class intent classifier (BGE-M3 + CatBoost, ~3.2K tickets) with Regex NER for order_id extraction, achieving 94% Accuracy, 0.91 Macro-F1, and ~95 ms p95 latency while cutting triage time to 1–2 seconds. • Production Lead Scoring System: Built an end-to-end lead scoring pipeline combining cargo deion embeddings (LaBSE-ru-turbo) with tabular/CRM features via CatBoost (~10K deals). Automated instant Telegram alerts for high-priority leads, achieving 88% Accuracy and 0.92 ROC-AUC. • Uplift Modeling for Promo Campaigns: Co-developed a customer selection model using a T-Learner architecture (CatBoost) to predict order probability with/without discounts. Deployed via FastAPI to CRM fields, achieving a +5 p.p. conversion boost (20% vs 15%) and reducing discount expenditure by 27%. • Internal RAG Assistant & Agents: Scaled production RAG serving 500+ DAU (15K+ docs, reducing research time by 40%) using dense/sparse hybrid search (Qdrant + BM25 + RRF + Cross-Encoder) that boosted accuracy from 62% to 89%. • Agentic Workflows & SFT: Developed multi-step agentic loops via MCP/FastMCP and fine-tuned Llama-3.1-8B-Instruct using QLoRA on domain datasets, increasing structured-response adherence from 78% to 91%. • MLOps & Evaluation: Built offline evaluation pipelines using Ragas (800 golden queries) and integrated end-to-end observability via ClearML and Langfuse, supporting continuous retraining and pruning optimizations that reduced inference costs by 30%. Skills Python (Asyncio) SQL Git Transformers PyTorch Hugging Face PEFT QLoRA BM25 RRF Cross-Encoder Reranking Query Rewriting Function/Tool Calling MCP REST APIs Docker Kubernetes (K8s) Celery Langfuse OpenTelemetry Language proficiency Intermediate English Native Russian Employment Employment Full, Part-time, Project-based Work format Remote Work schedule Flexible, Shift, 5/2 Relocation Possible Business trips Business trips possible