j
jacekgrotkowski

Jacek G

@jacekgrotkowski

AI Data Engineer

Poland
English
About me
I specialize in production-grade AI infrastructure and cloud data engineering for FinTech,Telcom and enterprise environments. With 5 years of experience at PwC, Accenture, PAYBACK, Amelco I build custom RAG systems (LangChain, Vector DBs) and cost-optimized data pipelines (dbt, Airflow, Snowflake/BigQuery). My focus is on clean code, automated validation, and predictable cloud costs. If you need a reliable AI assistant or a scalable data architecture - let's talk.... Read more

Skills

j
jacekgrotkowski
Jacek G
Offline • 

See my services

AI Integrations
I will create searchable ai memory from your recorded meetings

Portfolio

Work experience

Betsson_Malta

AI Data Engineer

Betsson Malta • Self-employed

Jan 2026 - Present7 mos

Description: Built scalable cloud data architecture and engineered end-to-end AI/LLM workflows for a high-volume FinTech platform. Key Responsibilities: - Automated unstructured data extraction and classification using Python, LangChain, and OpenAI/Claude APIs. - Orchestrated text embeddings and synced Medallion Gold-layer data to Vector Databases (pgvector/Pinecone) to power internal AI assistants. - Migrated legacy Snowflake pipelines to AWS, tuning S3 partitioning to resolve small file issues and drastically cut Athena costs. - Integrated LLM-based anomaly detection into Airflow DAGs while strictly managing API costs. Tech Stack: Python, LangChain, Vector DBs, OpenAI API, AWS (S3, Athena), Snowflake, Apache Airflow.

Data Engineer

PAYBACK • Full-time

May 2024 - Jan 20261 yr 8 mos

Focused on GCP architecture modernization and FinOps best practices. Executed large-scale migrations from Oracle to BigQuery, optimized dbt pipelines using incremental models, and tuned Cloud Composer resources. Implemented granular cost tracking and resource labeling via Terraform.

Accenture

Junior Data Engineer

Accenture • Full-time

Jan 2022 - Apr 20242 yrs 3 mos

Supported senior engineers in maintaining enterprise data solutions. Monitored Teradata ETL processes, managed task dependencies via Apache Airflow, and maintained technical documentation and data architecture diagrams for the engineering team.