Open to opportunities

Vyacheslav Lyubchenko

@vyacheslavlyubchenko

Message

AI Engineer shipping end-to-end LLM product features—reliable, testable, privacy-first.

Spain

Message

What I'm looking for

I’m looking for a role where I can ship end-to-end LLM features with strong eval/testing, privacy-first guardrails, and measurable reliability improvements—while collaborating with engineers and stakeholders to solve the real problem.

I’m an AI Engineer who ships LLM-powered product features end-to-end, from prototype to production. I design and build AI-enabled learning experiences—integrating LLM APIs, prompt-management, and structured-output workflows, plus retrieval over learning content and adaptive recommendations.

I balance fast experimentation with disciplined engineering: I build evals and test harnesses to measure output quality, consistency, and failure modes, then add guardrails, monitoring, and human-review steps before content goes live. My strength is full-stack delivery (TypeScript/Node.js, SQL, Supabase/PostgreSQL, REST APIs, Docker, cloud), paired with strong testing, privacy/security, and clear communication with non-technical stakeholders and education partners.

Experience

Work history, roles, and key accomplishments

Current

Founder & AI Engineer

Current

Taronja Spanish

Jan 2024 - Present (2 years 6 months)

Founded and shipped an AI-enabled Spanish-learning platform end-to-end, integrating LLM APIs with prompt management, structured JSON outputs, retrieval workflows, and adaptive recommendation. Engineered evaluation, guardrails, and human-review steps, and built the full stack using Supabase/PostgreSQL, REST APIs, and cloud deployment.

Prompt Management Structured Outputs RAG Real Time Grammar Feedback Consistency And Failure Mode Analysis GuardRails TypeScript SQL Supabase PostgreSQL REST APIs Docker cloud deployment Responsible AI

Project Manager (AI in SDLC)

EpicVin

Jul 2023 - Jun 2026 (2 years 11 months)

Integrated AI agents/LLMs into engineering and QA workflows and evaluated their reliability, quality, and cost in real use. Partnered with backend engineers on service architecture and data handling, translating stakeholder needs into technical scope and automating structured workflow improvements.

AI Agents LLM Copilot Cursor ChatGpt Claude Service Architecture Integration Workflow Automation Stakeholder Management

Project / Delivery Manager

RingCentral

Jul 2011 - Jul 2023 (12 years)

Worked across backend and cross-functional engineering teams on service delivery, integrations, data handling, and scalability for cloud SaaS. Built metrics and quality reporting systems, automated operational/reporting workflows, and led root-cause investigations to drive measurable improvements.

Cloud SaaS Service Delivery Integration Scalability Metrics And Reporting Workflow Automation Root Cause Analysis Operational Reporting

QA Automation / Process Engineer

Exigen

Jan 2008 - Dec 2010 (2 years 11 months)

Built QA automation and an automated results-collection and analysis system (an early evaluation/test harness) with stakeholder reporting. Ran root-cause analysis to improve quality and efficiency.

QA Automation Automated Results Collection Test Harnesses Root Cause Analysis Quality Improvement