Pavel Janata

Machine Learning • Data Science • he/him

Prague, CZ • pavel@janata.me • LinkedIn • Gitlab

Professional summary

Machine‑Learning engineer with 7+ years’ experience designing and delivering ML‑powered solutions end‑to‑end: from developing ML models to data ingestion, building complex streaming pipelines and deploying in cloud environment. Translates business requirements into robust, scalable production systems.

Core skills

Languages	Python, Scala, SQL
Python ecosystem	Scikit‑Learn, PyTorch, Darts, Pandas, Jupyter, Plotly, Dash, FastAPI, Pydantic
Data & Storage	DuckDB, PostgreSQL (Aurora), Cassandra, S3
Streaming & Processing	Apache Flink, Spark Structured Streaming, Kafka, Kinesis
Cloud & Ops	AWS (Glue, S3, RDS, Kinesis, CloudWatch), Kubernetes, Docker, GitLab Pipelines, GitHub Actions
ML Domains	Time‑Series Forecasting, Anomaly Detection, NLP / LLMs

Experience

Blindspot.ai

ML Engineer / Tech Lead

Part of Adastra Group
AI/ML consultancy

Prague · Jul 2018 – present (full‑time since Feb 2023)

Responsibilities

Technical delivery – architect streaming pipelines, develop & deploy ML models, perform data‑science experimentation; hands‑on coding (Python/Scala).
People leadership – mentor interns/juniors, conduct 1‑on‑1s, performance reviews and growth planning.
Pre‑sales & solution design – shape client needs into technical proposals.

2025–now Warehouse Resupply Forecasting · Data Scientist
Developed daily demand forecasting solution (Python, scikit‑learn)

2025–now EU AI Act compliance · AI Consultant
Provided best‑practice guidelines and tooling recommendations to meet EU AI Act transparency & risk‑management requirements for a major telco

2023–25 IoT Measurements Correction Platform · Tech Lead
Built Apache Flink pipeline for sensor data correction (Python Flink, AWS Kinesis, AWS Glue)

2023 Bank Balance Prediction · Data Scientist/Data Engineer
Design and develop real‑time balance forecasting using Spark Structured Streaming

2020-23 User & Entity Behaviour Analytics · ML Engineer/Data Engineer
Designed and delivered a cloud‑native, multi‑tenant anomaly‑detection platform running on Kubernetes (Flink, Kafka, Cassandra)

Education

2021-2023 Data Science Master Program at Open Informatics, FEE CTU
Thesis topic: Decentralized Federated Learning for Network Security

2019-2021 Artificial Intelligence Master Program at Open Informatics, FEE CTU
Unfinished

2016-2019 Informatics and Computer Science Bachelor Program at Open Informatics, FEE CTU
Thesis topic: Transfer Learning for Textual Topic Classificaton