Mark Vinogradov

Summary

I am an experienced software engineer with broad ML and LLM background. I've designed and implemented several scalable SaaS products, including LLM-powered retrieval systems, AI assistants and automated migration tools. My preferred language is Python, although I am familiar with Kotlin, Java and Golang.

My strongest quality as an engineer is that I can execute software projects end-to-end, including everything what is expected from industrial-quality product: architecture designs, neat and readable code, extensive multi-level testing, documentation, deployment and monitoring. As a bonus, my machine learning background helps tackle common challenges like train set annotation, model versioning, bias mitigation, scaling, performance monitoring, and LLM evaluation.

Outside of work, I dedicate most of my time to my family, but I also enjoy designing new quirky tabletop games.

Experience

SemaSoftware.com — Senior Python Engineer (Nov 2025 - Aug 2026)

Developed Liz AI Assistant: platform, R&D, integrations and MLOps.

Achievements:

Built the Liz Chat system end-to-end (architecture, deployment, monitoring): designed a unified retrieval layer with agent tools for fast search across differently structured data sources.
Jira, GitHub, Linear, Slack, Zoom, MS Teams. Serving ~20 enterprise clients across ~200 projects.
Implemented AI-powered report generation: sprint summaries, developer productivity metrics, project health dashboards etc.
Built Slack, Zoom, MS Teams integrations end-to-end; published Zoom Marketplace App.
MLOps: AI harness testing, semi-supervised user flow evaluations, dataset curation.

Datafold.com — Senior Python Engineer, fixed-term (Apr 2025 - Nov 2025)

Contributed to Data Migration Studio project -- an automated database migration tool, translating legacy SQL scripts into new SQL dialect scripts or dbt models.

Achievements:

Developed 90%-automated LLM-assisted database migration from SAP HANA / Informatica to Databricks.
Objects translated: ~250 column views, ~50 sprocs, hierarchy views, 4 NDSO pipelines etc.

Synthesized.io — Senior Backend Engineer (Oct 2023 - Apr 2025)

Rejoined to contribute to Python R&D backend, several pilot/demo projects and MLOps and infrastructure.

Achievements:

Built ML model quality monitoring pipeline reducing manual QA effort (Airflow, Spark, GCP).
Built natural-language-to-SQL generation service for automated test data creation (Langchain, gRPC) — Blog post

OneSoil.ai — Backend Engineer (Jan 2022 - Sep 2023)

Contributed to both backend (web app, async CPU-heavy task scheduler, other microservices) and ML submodules (yield productivity maps, yield data analysis, soil sampling).
Designed and implemented various other features (billing & monetization, monitoring, data anomaly detection etc.).

Achievements:

Collaborated with an agronomist to develop and implemented harvester's yield data analysis framework — ~100k users on over a million fields worldwide in 2022 — Blog post
Developed and implemented soil sampling method based on segmentation of the productivity map — main selling point for LATAM-based farming companies — Blog post
Refactored parts of existing Django application to reduce costs (~43% on AWS) and improve performance (~20% speed-up in data-heavy pipelines) while maintaining 99.9% uptime.

Synthesized.io — Backend Engineer (May 2020 - Jan 2022)

Developed Python & JVM-powered backend for SaaS cloud platform (GCP-hosted) providing ML model inference through a public API.

Achievements:

Built SaaS platform end-to-end: design, testing, deployment, monitoring.
Led multiple successful pilots (Deutsche Bank, UBS, UK W&P) — Blog post

Earlier Experience

Cobrain.io — Backend Engineer (2019 - 2020). Led a team of 3 building a medical data collection backend; managed hospital integrations from demo to contract.
Inspector Cloud — ML Intern → Full-stack Engineer (2016 - 2018). Object detection for retail; led automatic shelf monitoring project with X5.

Projects

Conflux: A two-player digital card game with deck drafting, real-time WebSocket gameplay, and an automated bug-fix pipeline where player feedback triggers a Claude Code agent to write failing tests, fix bugs, and open PRs. Built with Python/Starlette backend, vanilla JS frontend, and deployed via Docker Compose with a git push-to-deploy workflow. GitHub

EDH Pairings: A tournament management system for the competitive Magic: the Gathering EDH format in a four-man groups of players. Designed as a Django service with password-less authorization, server-side page rendering with REST API and simple mobile-friendly design. GitHub

Shooter: full-page site screenshot service: REST API and CLI-enabled tool that captures full-page or partial screenshots from URLs, detects and labels HTML elements, and performs scripted user actions during the process. Designed a scalable architecture with task brokering, enabling concurrent execution by multiple workers and delivering comprehensive outputs, including labeled images and JSON metadata. GitHub

Mark Vinogradov 👋

Summary

Experience

SemaSoftware.com — Senior Python Engineer (Nov 2025 - Aug 2026)

Datafold.com — Senior Python Engineer, fixed-term (Apr 2025 - Nov 2025)

Synthesized.io — Senior Backend Engineer (Oct 2023 - Apr 2025)

OneSoil.ai — Backend Engineer (Jan 2022 - Sep 2023)

Synthesized.io — Backend Engineer (May 2020 - Jan 2022)

Earlier Experience

Technical Skills

Projects

Education

Awards

Other