COMMUNITYAskapro
Meber iconMeber thumbnail
Job icon
Machine Learning EngineerYandex Zen

Andrey

Machine Learning Engineer with over 5 years of experience delivering scalable, high-impact AI solutions in both agile startups and large-scale enterprises. I specialize in Natural Language Processing and Recommender Systems, where I've successfully engineered models that drive significant business outcomes. I am passionate about innovation and continuously track emerging trends and technologies, sharing my knowledge through professional conferences and personal projects.
ML engineer
Natural Language Processing
Recommendation Systems
Large Language Models (LLM)
Benchmark Coverage Optimisation
Ranking Optimisation
Back Translation
Language Translation Systems
Compiler Development
AST Parsing
Search Algorithms
Logistics Optimization
Entertainment
Media
AI
Artificial Intelligence
Telecom
E-Commerce
Global
Russia
Enterprise
Research and Development
News & Content Platform
LLM Pretraining Pipeline
C to Eolang Compiler
Product Search
Web App
Data Pipeline
Compiler
Marketplace Platform
Python
Pandas
Hydra
TensorFlow
Scipy
Numpy
MapReduce
C++
Clang
PostgreSQL
FastAPI
Docker
Tensorboard
Wandb
Git
B2C
Internal product
B2B
Show more
Open to
Employment
Contract
Andrey's timeline
Job icon
ML engineerYandex Zen
September 2022 - Present
Natural Language Processing
Recommender Systems
Entertainment
Global
Enterprise
  • Engineered a SOTA multi-document summarization model for news aggregation, achieving an 87% human acceptance rate with less than 1% critical errors.
  • Designed and implemented automated news timelines for evolving events, resulting in a 2.8% increase in content depth and a 1.4% boost in user time spent.
  • Optimized ranking algorithms, driving a 4.3% increase in daily active users (DAU) and a 2.1% uplift in user engagement.
  • Enhanced news clustering pipelines, improving the F1-score from 0.91 to 0.95.
Job icon
ML engineerYandex GPT
March 2021 - August 2022
LLM Pretrain
Technology
Global
Enterprise
  • Developed and deployed large-scale text corpus deduplication, boosting assessor F1-score from 0.77 to 0.82.
  • Optimized benchmark coverage by training a classifier, improving dataset relevance for pretraining tasks.
  • Created a dataset augmentation pipeline using Back Translation, increasing pretraining robustness.
  • Enhanced document parsing quality, resulting in a 3% faster model convergence during training.
Job icon
ML engineerWBprod
April 2020 - February 2021
Marketplace Optimization
E-Commerce
Global
Medium-sized business
  • Developed a search robot for products, increasing cold client conversions by 4%.
  • Created a report monitoring system for item positions.
  • Developed an advanced route-planning algorithm for courier logistics, increasing daily pickup points by 13%.
  • Added generation of invoices for product stock, increasing the speed and accuracy of the product acceptance process by 15%.
Job icon
Software DeveloperHUAWEI
June 2019 - March 2020
Compiler Development
Technology
Global
Enterprise
  • Implemented processing of all basic data types from Clang AST to Eolang.
  • Developed a mechanism for translating multidimensional arrays to Eolang.
  • Developed a mechanism for translating Enum types to Eolang.
Show more
Andrey's cases
Show more