Stanislav Liashkov

ML Engineer

Zypl.ai

R&D Lab with a focus on outlier-resistant AI applications in finance, government and education.

Adapted and evaluated LLMs for Tajik, built training and inference infrastructure, and worked on research papers.

• Worked on Project SoroLLM with UNICEF, adapting large language models to Tajik, a low-resource language, and implementing an end-to-end training pipeline with continued pretraining using LoRA, instruction fine-tuning, and Direct Preference Optimization (DPO). • Built text filtering and cleaning pipelines and generated synthetic data using proprietary and open-source LLMs. • Set up, maintained, and monitored ML infrastructure and training jobs on AWS SageMaker and an on-premises server with 8 H200 GPUs.

AI Engineer

TWS Labs (AiXpert)

B2B AI-driven Legal Compliance System for Russian Enterprises

Built legal-document retrieval, embedding, and evaluation systems; improved ranking benchmark MAP by 20.6%.

• Built a knowledge base of more than 200,000 Russian legislative documents and 3 million-plus vector database chunks, enriched with metadata for search and filtering. • Implemented a legal assistant workflow for multi-step retrieval of legislation and case law with corrective reasoning, using LangChain, LangGraph, Qdrant, and LLaMA 3. • Trained a legal-document embedding model on synthetic triplets, improving mean average precision by 20.6% on a ranking benchmark.

ML Engineer

Relog.ai

Transport management system provider specializing in last-mile logistics

Built a Text-to-SQL copilot credited with saving about 182.6 analyst-hours monthly, alongside data pipelines and a traffic forecasting baseline.

• Developed an in-house Text-to-SQL AI copilot for data analysts using RAG, tool-calling, and LLaMA 2, reducing BI report delivery time and routine queries by an estimated 182.6 analyst-hours per month. • Built data pipelines to integrate CRM data from Bitrix24 into Power BI. • Built a baseline model to forecast road-edge congestion in Almaty, combining time series, LISA, and supervised machine learning.

Junior Data Scientist

AI Flow LTD

Consulting company delivering data-driven solutions in BI

Contributed to churn modeling, ETL pipelines, and automated data-quality and drift detection.

• Contributed to a churn prediction model using LightGBM, Polars, SQL, Optuna, and MLflow to support targeted marketing strategies for a client. • Implemented ETL pipelines with Python, dbt, and Apache Airflow. • Built automated data-quality and drift-detection frameworks for ML inference using Great Expectations, Pandas, and SciPy statistical tests.

Master’s degree, Data Science

University of Colorado Boulder

Bachelor equivalent, Computer Science

42 Bangkok