Skip to content

ML ENGINEER / DATA SCIENTIST

Gonchar Daniil

I work on tasks of any complexity and domain

Contact
Download CVCV preview
  • NLP · LLM · RAG

01 / Expertise

Areas of expertise

LLM & RAG / CorpGPT

01

Corporate RAG systems for search across Confluence, DWH, SQL data marts, PDFs and scans. I separate the offline knowledge pipeline from the online answer flow.

Hybrid retrievalLLM rerankingVersion-aware retrievalContext tighteningSource attribution

I control versions and access, combine dense and sparse retrieval, narrow a broad candidate pool through LLM reranking, and generate answers only from compact context with mandatory source attribution.

Stack

bge-m3 + BM25Qdrant · HNSWQwen3-NextStructure-aware chunkingSchema-aware promptingDocling + EasyOCR

AI Agents

02
Tool orchestrationStateful workflowsDependency graphsSafe executionEarly stop

NLP & Document Intelligence

03
NERLayout parsingOCRDoclingEasyOCR

Production ML

04
Model servingStreaming pipelinesInference optimizationExperiment trackingDrift monitoring

02 / Projects

The approach, told through real problems

Case 01

CorpGPT Knowledge RAG

Search across Confluence, DWH, SQL, tables and scans.

Case 02

Data Change Analysis Agent

Explain changes in data marts and calculations.

Case 03

Data Incident RCA Agent

Find root causes of data degradations across ETL, releases, SLA and lineage.

Case 04

Document Intelligence Pipeline

Extract data from unstable PDFs, tables and scans.

03 / Testimonials

Words from colleagues and partners

Testimonials from colleagues and partners will appear here once publication is approved.

Leave a testimonial

Testimonials are not published automatically. After submission Daniil reviews it and decides on publication.

0 / 1000 characters
UI prototype: simulate response

No data is sent anywhere.

04 / Contact

Have an ML, NLP, or LLM challenge? Let's talk.

Choose a convenient way to get in touch or explore a professional profile.

Download CVCV preview