Data Engineer & Product Builder
13 years in agriculture — five walking fields as an agronomist, eight building data products for agtech. I deploy complete data stacks — Airflow, Superset, DuckDB, AI agents, computer vision — and ship fast: prototype today, validate tomorrow, iterate next week.
What I Do
I turn business questions into metrics, metrics into dashboards, and dashboards into automated workflows. I own the problem end to end: pipelines, analytics, AI agents, servers — if it needs building, I build it and ship it.
My edge is the combination. Most engineers need a domain expert to explain agriculture — I am one: I've built yield maps from combine sensors in the field, and the segmentation models that read those same fields from space.
Experience
Sole data engineer — built the company's entire data platform from scratch and run it end to end.
- 100+ Superset dashboards and 80+ Airflow DAGs serving every department.
- Shipped Agroplanerka solo — a plan/fact/forecast product for field operations: Monte-Carlo completion-date forecasts, earned-schedule triage (EVM/TSPI), equipment-capacity balancing, crop-loss cost ranking.
- AI agents in production — notifications, accounting automation, field monitoring.
- Geospatial pipeline — satellite remote sensing on DuckDB, field segmentation with SAM and U-Net.
- B2B product analytics and customer-health monitoring.
- Own the infrastructure — CI/CD, deployments, servers, backups.
Tools: Apache Airflow, Apache Superset, DuckDB, PostGIS, Python, FastAPI, Image Segmentation (SAM, U-Net), AI Agent Frameworks, ECharts, CI/CD, Git, Linux
Co-founded and took the product from zero to market. Designed it end to end with a designer in compressed sprints, then shipped the MVP fast — Superset + a Python Telegram bot delivering crop-sensor data and satellite-imagery analytics to farmers. Worked with ML engineers on phenological-stage labeling in Label Studio.
Presented Cropler at Agritechnica in Hannover — the industry's largest trade fair — generating strong interest and key dealer contacts. Owned roadmap, backlog, marketing campaigns, and sales-channel expansion.
Data labeler → team lead → sole PM in under a year. Agronomic background gave me an edge — I understood the users because I was one of them.
Built the geospatial data pipeline for OneSoil Map: search, labeling, QA, inference support. Led mapping team, then took over product: user research, A/B testing, feature specs, backlog. Six months as the only PM on the platform.
Drove significant increase in data completeness through targeted features. 40+ Superset dashboards used daily across all departments. Compiled agronomic reference books that became core platform data.
Tools: QGIS, GDAL, PostGIS, Python, Jupyter, Google Earth Engine, PostgreSQL, BigQuery, Apache Superset
Five years across three organizations: seed production, feed production, precision agriculture. Yield mapping with Claas, Trimble, and New Holland harvester sensors; variable-rate fertilizer maps built from satellite imagery; electronic field records and GIS monitoring. This is where I earned the domain expertise that everything above is built on.
Skills & Stack
Apache Airflow, Apache Superset, DuckDB, PostgreSQL, Python, ETL pipelines
BigQuery, data modeling, ad-hoc analysis
AI agent frameworks, LLM integration, agent memory & skills, rapid prototyping
Speech AI (Whisper, speaker diarization), custom AI tool integrations, Telegram bots
PostGIS, GDAL, QGIS, remote sensing, image segmentation (SAM, U-Net)
Google Earth Engine, multispectral imagery, yield mapping
Product strategy, product analytics, B2B & B2C, rapid MVP development
A/B testing, user research, backlog prioritization
CI/CD, Git, Linux, Docker, server administration, deployments, backups
Precision Agriculture, Crop Monitoring, Phenology, Agrochemistry
Personal Projects
Built in my free time, solo, end to end — every product below is live in production.
Geospatial platform that turns raw precision-agriculture data into interactive maps. Built end-to-end — a self-written yield-processing engine (cleaning, calibration, management-zone delineation) exposed as an API, a non-buffering streaming proxy for field archives up to 4 GB, and an async tiling pipeline serving PMTiles to a MapLibre client with choropleth analytics. Mobile-first, 8-language UI — mapagtech.pilip.io
Community cycling-route map — discover, build, and share rides. Built end-to-end: a multi-profile routing engine (road / gravel / MTB / walking) that snaps drawn tracks to the road network, a drag-and-drop route builder with free-form off-road drawing and automatic ring-route generation, and a viewport-driven route feed. Rich cartography — elevation & gradient profiles, a ridership heatmap, 3D relief, topographic and satellite layers. One-click export to GPX / FIT / TCX / KML / GeoJSON tuned per device (Garmin, Wahoo, COROS, Karoo), plus a Telegram bot for sharing and import — nakat.bike
Free AI transcription service focused on speaker diarization and voice recognition — identifies who said what, recognizes returning voices across recordings, and produces clean per-speaker transcripts. Audio/video to text, summarization, 90+ languages. Runs on my own self-hosted Whisper + diarization inference API — voxprint.app
Telegram bot for audio/video transcription and summarization — voice → text → insights. 2K MAU at peak, 1K+ MAU today, organic growth only, zero ad spend. Runs on the same self-hosted speech API as VoxPrint — @VidVKYT2AudioBot
AI-powered manga translation platform — OCR, translation, and image generation, with every step under the translator's control — inkover.ink
Rental-market analytics for Belarus — data-collection pipeline, AI classification of apartment quality, duplicate detection, market dashboards — rent-stat.org
EV catalog for Belarus — specs, prices, safety ratings, owner reviews, market analytics. Content is maintained by an autonomous agent pipeline — evauto.pro
AI platform for SMM automation — content plans, post generation, scheduled publishing to Telegram, VK, Dzen, OK — socribo.ru
Education
Workforce Management in the Agricultural Sector (second degree)
Technology for Storage and Processing of Plant Raw Materials
Let's talk
Interested in working together? Reach out directly.