Labaschin
Principal ML/AI Engineer · Data Lead · Founding Engineer
I’m an MLE passionate about using machine learning and generative AI to transform technical challenges into high-impact solutions. I thrive on building software systems that deliver tangible results, pioneering enterprise-scale GenAI platforms, and developing ML systems that drive millions in business value.
Highlights
Workhelix
Founding ML Engineer. Enterprise GenAI platforms from seed to $75M Series A, backed by Andrew Ng, Mira Murati, and Yann LeCun.
O’Reilly Media
2 published reports on AI agents. 1 book in progress: Agent Memory — Building Stateful AI Agents That Remember, Adapt, and Work Across Time.
AEA Papers & Proceedings
1 peer-reviewed publication extending “GPTs Are GPTs” to measure firm-level LLM exposure.
Talks & Guest Lectures
7 appearances across 6 venues: ODSC West, Wharton, AI.Science, Normconf, MLOps Community, and Into the Hopper podcast.
USPTO Patents
2 patent applications: Shared Mobility Simulation and Prediction System, and Matching Drivers With Shared Vehicles.
Industry Experience
9 years building production ML systems across 5 companies, from telematics risk modeling to enterprise LLM platforms.
Current Focus
Building
Enterprise GenAI
Founding engineer at Workhelix, building the Nucleus platform that helps enterprises measure and grow AI ROI. Async LLM APIs, embedding pipelines, and agent deployment for Fortune 50 customers like Autodesk and Nasdaq.
Founding Engineer
Writing
An O’Reilly Book on Agent Memory
Writing Agent Memory: Building Stateful AI Agents That Remember, Adapt, and Work Across Time for O’Reilly. Previously published two O’Reilly reports on AI agents and co-authored AEA research on how LLMs reshape firm-level labor exposure.
Book in progress
Speaking
What’s Next on Stage
Turning the Agent Memory book into live talks: how to build AI agents that persist state, manage context, and work across sessions. Speaking throughout 2026 at conferences and meetups. Interested in having me speak? Let’s talk.
2026 engagements open
Experience
Founding Engineer, Principal ML/AI Engineer, Workhelix
Apr 2022 — Present- Founding Engineer: Leads core platform development at Workhelix, parallelizing highly scalable async LLM APIs and custom SOTA embedding systems, building and maintaining our internal LLM and agent deployment platform for Fortune 50 enterprise customers.
- ML/GenAI Analytics Platform: Architects multi-container Docker system for real-time data embedding and workflow analysis, combining proprietary "task" classification algorithms with predictive models (PyTorch, FastAPI, AWS ECR/ECS).
- Analytics & Insights: Develops novel complexity metrics to quantify and forecast GenAI’s impact on engineering workflows, enabling data-driven insights on productivity for enterprise customers.
- API Architecture & Data Pipeline Engineering: Engineers high-throughput GitHub/GitLab extraction system with async rate limiting and GraphQL cursor pagination, building robust task queues/concurrency controls that reduced repository processing time from 30 to 2 minutes.
- Seed to Series A Growth: Drives critical technical development that enabled Workhelix’s growth from seed to Series A ($75M valuation), attracting investment from AI leaders including Andrew Ng, Mira Murati, and Yann LeCun.
Senior Data Scientist, Hopper
Aug 2021 — Apr 2022- Strategic Partnership Leadership: Led ML engineering for Capital One Travel partnership, creating foundational ML systems that helped secure a $96M investment and drove Hopper Cloud to 40% of company revenue.
- Technical Architecture: Designed and implemented multi-tenant ML systems including multi-arm bandits and price freeze algorithms using GCP, enabling secure and scalable travel booking solutions for enterprise partners.
- MLOps Innovation: Spearheaded DevOps/MLOps implementation for Hopper Cloud, establishing CI/CD pipelines and orchestration workflows with GitHub Actions and Kubeflow to support rapid scaling of the B2B platform.
Data Scientist, XPO Logistics
Jan 2021 — Aug 2021- Cost Optimization & ML Systems: Delivered $8M in savings through optimized shipment prioritization and automated pricing systems, a result from spearheading A/B testing and ML initiatives using XGBoost.
Data Scientist, Revantage (Blackstone)
Oct 2019 — Jan 2021- Investment Analytics: Led A/B testing with power analysis and regression modeling to optimize real estate investment decisions, driving multi-million dollar property savings.
- Analytics Engineering: Developed Python analytics pipeline (scipy, scikit-learn) for apartment renovation ROI analysis and geodata-based warehouse investment models.
Economist Researcher / Data Scientist, Arity (Allstate)
Sep 2017 — Oct 2019- Risk Innovation: Pioneered telematics-based risk modeling for shared mobility companies, resulting in two patent applications and creating a new business vertical.
- Innovation Recognition: Won 2019 Hackathon for AWS-based NLP modeling, with research featured in Business Insider.
Adjunct Lecturer, Chapman University
Aug 2023 — Dec 2024- Developed and taught Python-based AI/ML curriculum to 30+ students, bridging academic concepts with industry applications, lessons and course materials.
Publications & Talks
The Evolution of AI Agents (Into the Hopper Podcast)
Into the Hopper Podcast
Building Stateful AI Agents: Memory Management & Optimization with LangGraph and Redis
ODSC West 2025
Managing Memory for AI Agents
O'Reilly Media
AI Needs Memory: Here's How It Works
MLOps Community
Extending 'GPTs Are GPTs' to Firms
American Economic Association: Papers and Proceedings
Building With AI: How I Build Quick POCs with LLMs (Wharton Guest Lecture)
Wharton Guest Lecture
Building a RAG Model
YouTube Workshop
A Normie Approach to Validating LLM Outputs (AI.Science Talk)
AI.Science
What Are AI Agents? When and How to Use LLM Agents
O'Reilly Media
Building an HTTPS Model API for Cheap: AWS, Docker, and the Normconf API
Normconf
Technical Skills
Programming
Python, Java, C#, R, SQL, Shell, JavaScript, CSS, HTML
AI / ML
GenAI (Llama, Mistral, OpenAI, Claude), Fine-Tuning, PyTorch, TensorFlow, Deep Learning, Transformers, NLP, Machine Learning, Ensemble Methods, Boosted Trees
Distributed Systems
PySpark, Hadoop
Cloud
AWS, GCP, Azure
Deployment
GitHub Actions, GitLab, Docker, FastAPI, Flask, Modal
Databases
PostgreSQL, MySQL, DuckDB, BigQuery, Databricks, Snowflake, Athena
Education
B.A. Economics, cum laude
Lake Forest College, Lake Forest, Illinois — 2016
Patents
USPTO 20190347941