- Designing a multi-turn LLM search agent integrated with Coveo's retrieval and indexing stack.
- Built an evaluation and alignment pipeline to measure model adherence to behavioral guardrails and custom preference specifications.
- Initiated the PsychoPass project: geometric profiling of adversarial multi-turn LLM conversations for early jailbreak detection.
About
ML scientist with research and industry experience in graph learning and applied AI. I am pivoting to AI safety research, with recent work on LLM jailbreak detection, agent alignment evaluation, and graph-based risk detection. Currently an Applied Scientist at Coveo, where I work on multi-turn search agents and LLM evaluation pipelines.
Publications
-
8
PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations
-
7
Understanding the Design Principles of Link Prediction in Directed Settings
- 6
- 5
- 4
- 3
- 2
-
1
Interactive Evolutionary Approaches to Multi-objective Feature Selection
Experience
Coveo
Feb 2026 – Present
Applied Scientist
Montreal, QC, Canada
Block
Feb 2024 – Oct 2025
Machine Learning Engineer
Montreal, QC, Canada (Remote)
- Led fine-tuning of the Foundational Events Model — a large-scale transformer encoding user activity sequences into user embeddings — for account takeover and chargeback detection.
- Applied inductive GNNs at scale to identify gambling activity and referral abuse in transaction networks.
- Developed anomaly detection on time series of customer location signals (Customer Journey).
Block
May 2023 – Dec 2023
Applied Deep Learning Intern
Montreal, QC, Canada (Remote)
- Formulated real-time chargeback detection as a temporal graph learning problem and developed a novel deep learning architecture for this task.
- Work resulted in publications in TMLR and DMLR.
Segmentify
Jan 2018 – Aug 2018
Data Scientist
Istanbul, Türkiye
- Built a customer segmentation framework encoding purchasing behaviour for lifetime value estimation, supporting e-commerce retailers in boosting conversion rates.
Education
McGill University
Jan 2019 – Dec 2023
Ph.D., Computer Engineering
Montreal, QC, Canada
- Thesis: Graph-Based Strategies for Classification with Diverse Label Information.
- McGill Engineering Doctoral Award (MEDA).
University College London
Sep 2016 – Dec 2017
M.S., School of Management
London, UK
- Fully funded by UCL studentship.
Middle East Technical University
Sep 2014 – Jun 2016
M.S., Industrial Engineering
Ankara, Turkey
- Dean's Honour List; fully government-sponsored.
Middle East Technical University
Sep 2010 – Jun 2014
B.S., Industrial Engineering
Ankara, Turkey
- Dean's High Honour List.
Blue Dot Impact
2025
Certificate — Technical AI Safety
Online
- Intensive course on AI alignment, interpretability, and AI safety research methods. Verified certificate.
Skills
Languages
Core ML
Agentic / Safety
MLOps