Bohdan T. — AI/ML Engineer / Full Stack Developer

Work Experience

AI/ML Engineer (Interactive Real-Time Video Avatar with Lip-Sync)

Duration: 1 year
Summary:

• Built an AI-powered real-time video avatar capable of natural interaction with users, featuring precise lip-sync aligned to generated or user-provided speech
• The system combined face animation models, audio-to-visual synchronization, and dynamic response generation, enabling the avatar to hold live, human-like conversations
• Integrated speech synthesis, real-time rendering, and dialogue management to deliver smooth and responsive user experiences

Responsibilities:

• Developed a live animated video avatar supporting real-time interactions with accurate lip-sync;
• Integrated audio-driven facial animation models to map phonemes to mouth shapes and facial expressions;
• Implemented pipelines for speech-to-text, LLM-based response generation, and TTS audio synthesis;
• Optimized avatar rendering for low-latency streaming and synchronized audio-visual output;
• Built APIs and orchestration logic to manage conversations, avatar states, and user context.

Technologies: Python, FastAPI, PyTorch, OpenCV, SyncTalk, InfiniTalk, RunPod, Librosa, aiortc, ElevenLabs, Groq, WebRTC, FFMPEG, Docker, GPU acceleration

AI & ML Engineer (AI-Powered Modular Workflow System)

Duration: 1 year
Summary:

• Designed and implemented a modular multi-agent workflow system capable of executing complex pipelines either through predefined plans or dynamic orchestration by an agent controller
• Integrated the MCP library with server-side connectors for PostgreSQL, S3, and Brave Search, enabling agents to retrieve, store, and process data autonomously

Responsibilities:

• Designed and deployed a multi-agent orchestration system built around hybrid agent-orchestrators with support for modular workflows;
• Integrated the MCP library with server-side connectors;
• Built API endpoints and controller logic in FastAPI to enable smooth orchestration;
• Connected agents to PostgreSQL and S3 for persistent storage, as well as to Brave Search for data enrichment;
• Ensured robust data validation and serialization using Pydantic models.

Technologies: LlamaIndex, OpenAI, MCP, FastAPI, Postgres, Pydantic, Docker, n8n

AI/ML Engineer (AI-Driven Ad Bid Price Optimization Model)

Duration: 1 year
Summary:

• Developed and trained a machine learning model to predict the most optimal (lowest effective) bid price for digital advertising campaigns
• The system analyzed historical performance data, market dynamics, and contextual features to generate accurate price recommendations aimed at maximizing ROI while minimizing ad spend
• Implemented a full ML lifecycle – from data preparation and feature engineering to model training, evaluation, and deployment

Responsibilities:

• Designed and trained ML models to forecast the optimal minimum bid price for advertising placements;
• Performed data preprocessing, feature extraction, and time-series enrichment using historical campaign data;
• Evaluated multiple model families (regression models, tree-based methods, and gradient boosting) to identify the best-performing approach;
• Implemented automated pipelines for model training, validation, and hyperparameter tuning;
• Deployed the final model into production with monitoring for prediction stability and performance drift.

Technologies: Python, Scikit-learn, XGBoost/LightGBM, Pandas, NumPy, Docker, AWS Lambda, Autogluon

Full Stack Python Developer (Enterprise Web Platform Development & Maintenance)

Duration: 1 year
Summary:

• Developed and maintained a large-scale web platform for an enterprise client specializing in cloud and on-premise infrastructure solutions
• The project involved creating user-facing interfaces, internal dashboards, and configuration tools used by corporate customers to manage cloud services, monitor system performance, and streamline operational workflows
• Focused on delivering a stable, scalable, and intuitive front-end experience aligned with enterprise standards

Responsibilities:

• Designed and developed both frontend and backend features for the enterprise platform;
• Built and maintained RESTful APIs and integrated them with frontend components;
• Implemented business logic and data processing on the backend using Python;
• Developed reusable UI components, optimized performance, and ensured consistent UX;
• Collaborated closely with designers, frontend, backend, and DevOps teams;
• Ensured code quality through reviews, refactoring, testing, and optimization;
• Followed enterprise standards for security, scalability, and maintainability.

Technologies: Python, REST APIs, JavaScript / TypeScript, HTML, LESS (CSS), Nunjucks, Redux, SQL/Databases

Education

• Master’s degree Ivan Franko National University of Lviv
  Philology (Japanese)
  
• Bachelor’s degree Ivan Franko National University of Lviv
  Philology (Japanese)