Aleksandrs Berezņickis

Principal AI Engineer

Simform

May 2024 - Current (2 years 2 months)

Architected and led Teaching Voice Assistant leveraging LangChain, LangGraph for agent orchestration and LiveKit for real-time communication, integrated with OpenAl models and Coqui STT/TTS, with a curriculum-aware hybrid RAG architecture.Led the development of 5+ LLM-based teaching specialist agents built on MCP servers to provide secure, standardized function calling and DB connection interfaces, with an intelligent routing layer that dynamically dispatches queries to the best-fit agent based on context.Designed and constructed a hybrid RAG architecture for an AI tutor, integrating semantic vector retrieval, curriculum-aware metadata filtering, keyword searching retrieval (BM25) and Sentence-BERT re-ranking to improve answer relevance.Bui

A

Senior Machine Learning Engineer

Andor Health

Sep 2022 - May 2024 (1 year 9 months)

Led the development and deployment of healthcare voice assistant powered by Multi-component Architecture (ASR, LLM, TTS) using LLM orchestration frameworks like LangChain, LangGraph and Livekit with ReAct and Chain-of-Thought method, utilizing the Hybrid RAG.Fine-tuned over 10 open LLMs (Llama, Qwen) for adopting own healthcare datasets and conversational AI using QLoRA on Amazon SageMaker, reducing memory usage up to 90%, speed up 3x training duration.Utilizing pre-retrieval techniques like chunking strategies, metadata extraction and query optimization to construct Hybrid RAG leveraging PostgreSQL and FAISS, boosted retriever performance through integrating ColBERT re-ranker as a post-retrieval to reduce non-grounded (hallucinated) respon

Machine Learning Engineer

Eleks

Jan 2020 - Aug 2022 (2 years 8 months)

Fine-tuned 5+ LLMs using LoRA, model selection for efficiently extracting and summarizing information from extensive document sets, while effectively removing jargon and irrelevant contents, optimized OCR through model optimization (like pruning, quantization), reducing latency by 35% significantly enhancing real-time processing.Developed a Name Entity Recognition (NER) system for e-commerce, achieving an F1 score of 95% for entity identification, improving 2% revenue growth.Created a sentiment analysis engine that processes 8,000 daily customer reviews using Tensorflow, Spacy and NLTK, achieving 95% accuracy in product development and achieving ROUGE-1 score 41 for 35,000 product description per day.Implemented a masked face recognition sy

Machine Learning Engineer

Facebook

Jan 2016 - Dec 2019 (4 years)

Leveraged Tableau for exploratory data analysis (EDA) to help the data science team uncover actionable insights, streamline feature selection, and validate hypotheses faster, which accelerated model development cycles.Built robust ETL pipelines incorporating dimensionality reduction techniques (PCA, t-SNE, UMAP) to enhance data quality and interpretability using frameworks like Pandas, Pyspark and tools like Kafka and Airflow.Developed a customer activity prediction system with XGBoost using frameworks like Scikit-learn and MLflow, achieved 92% classification accuracy, enabling proactive engagement strategies.Developed automatic License/Number plate recognition using OpenCV and YOLO5, optimized it for mobile apps using python frameworks suc

Aleksandrs Berezņickis

About

Detail

Timeline

Résumé