Eva Agapaki, Ph.D.

Senior Data Scientist • LLMs, RAG, Knowledge Graphs

New York, NY

(857) 399-7321 agapakieva@gmail.com linkedin.com/in/eva-agapaki

Summary

Data Scientist with 8+ years of experience developing and deploying ML and generative AI solutions, specializing in LLM-powered retrieval, embeddings, knowledge graphs, and agentic data enrichment pipelines. Led full-stack ML development across Fortune 100 companies, from model design and experimentation to evaluation, deployment, and cross-functional integration with product and engineering. Hands-on experience with LLMs, multimodal embeddings, vector databases, RAG, knowledge graphs, and ML-driven recommender systems. PhD in Computer Vision (MIT & University of Cambridge).

Technical Skills

Languages & ML: Python, SQL, Cypher, scikit-learn, PyTorch, TensorFlow

Generative AI: LLMs, RAG, Embeddings, LangChain, GenAI evaluation

Platforms & Infra: Vertex AI, Neo4j, Vector DBs, Git, GCP/AWS/Azure, APIs, Game engines

Education

University of Cambridge & MIT
Ph.D., Computer Science (Computer Vision)
Thesis: Automated Object Segmentation in Existing Industrial Facilities
UCLA
M.S., Civil & Environmental Engineering
University of Patras
B.S., Civil Engineering

Awards

PTC Best Innovation Award
ML-driven AR product that improved factory-floor training efficiency through real-time computer vision inference and interactive guidance.
Charles M. Vest Fellowship
Only Ph.D. student selected across all UK universities to continue doctoral research at MIT, awarded by the U.S. National Academy of Engineering.
Space Research Initiative Award (NASA)
$100K funding to develop Geometric Digital Twins of Space Assets.

Publications

Google Scholar Profile

Current Experience

Senior Data Scientist

IKEA (Contract) • New York, NY

Nov 2024 – Present

Scope, research and develop data science projects for product and engineering to improve recommender systems' retrieval and relevance metrics.
Design and implement embedding- and LLM-based retrieval algorithms to enhance product relevance in recommendations.
Build a knowledge graph integrating structured and unstructured data (images, PDFs, 3D assets) to improve retrieval of product recommendations.
Develop agentic flows for automated data annotation (relationship inference from unstructured data) with ~70% expected reduction in manual labeling.
Partner with engineering to productionize ML prototypes and integrate them into IKEA's personalization ML stack.

Senior Data Scientist

Capgemini Invent • New York, NY

Nov 2024 – Present

Incubate GenAI and ML solutions for Fortune 100 clients by developing reusable assets (RAG pipelines, LLM agents, evaluation frameworks) and guiding AI roadmap decisions through data-driven maturity and feasibility tools.

Founder & CEO

Hatch Labs • New York, NY

Sept 2023 – Present

Build an enterprise product portfolio on LLMs, RAG systems and conversational chatbots for pre-seed to seed stage startups and SMBs.
Define and articulate the company's vision, business model and strategic direction in alignment with generative AI market opportunities, governance and the AI value chain (MLOps, data pipelines, product requirements).
Develop product evaluation frameworks to derisk product launches.

Past Experience

Head of Product

Next Millennium Media • New York, NY

Jan 2023 – Sept 2023

Managed a global engineering and data science team (15 engineers, 2 DS, 2 PMs, 1 UX) building supply-side auctions, A/B testing, and SSP/DSP launches.
Led data-driven development and experimentation, increasing user adoption by 80% and driving +150% revenue growth in Q2 2023 through analytics-based prioritization and rapid iteration.
Delivered ML-powered models for ad revenue optimization, audience targeting, and ad-quality scoring achieving ~$1.5M in incremental revenue.

Founding Scientist & AI Lead

Tenet Twin LTD • London, UK

Sep 2019 – Mar 2023

Built and launched an AI-powered Digital Twin platform (computer vision + predictive modeling) that transformed industrial asset monitoring with real-time, ML-driven insights adopted by two major oil & gas enterprises.
Led high-stakes B2B pilots from concept to paid software licensing, validating model performance on live operational data and rapidly iterating with engineering to improve accuracy, usability, and adoption.

Assistant Professor & Director of Digital Twins Lab

University of Florida • Gainesville, FL

Nov 2021 – Feb 2023

Led applied research and industry partnerships to build and deploy AI/ML-powered Digital Twin MVPs for federal, state, and private organizations driving $1.9M in funded projects and enabling adoption of AI for operational efficiency and sustainability.
Developed AI-driven data science and simulation tools using ML, computer vision, and predictive modeling for construction, engineering, and transportation with partners including NVIDIA, McKinsey, U.S. DOT, NREL, and DFW Airport.

Senior Data Scientist

PTC • Boston, MA

Jan 2020 – Jul 2021

Led the end-to-end development of an ML-powered API and AR/VR computer vision product, integrating Azure Custom Vision with PTC platforms to deliver real-time object detection for industrial training and operations.
Built and scaled a cross-functional ML product team from 0→32 (DS, Engineers, UX), driving fast experimentation, model evaluation, and MVP delivery aligned with executives.