Hi, I'm Lookinder Kumar
Building intelligent systems at the intersection of AI, data, and regulated industries.
About Me
AI Engineer building intelligent systems at the intersection of AI, data, and regulated industries.
Lookinder Kumar
AI Engineer & MSc Student
My Story
My work sits at the intersection of machine learning, explainable AI, and real-world financial systems. I'm drawn to problems where getting the model right isn't enough — where the explanation matters as much as the prediction, and where a wrong answer carries real consequences.
My MSc at Griffith College Dublin, awarded First Class Honours, investigated adversarial robustness and SHAP explanation stability in fraud detection models mapped against EU AI Act 2024 compliance requirements. The core finding — that adversarial attacks don't just fool the model, they invert the explanations a fraud analyst sees, while looking completely normal — sits at the heart of why I care about AI systems that are auditable, not just accurate. I've also published research at IEEE ASPCC 2024 and Springer CIPR 2024.
Before Dublin, I completed my BTech in Computer Science & Engineering at C.V. Raman Global University, India (First Class Distinction, CGPA 8.50/10), and worked as a data analyst across financial and commercial datasets. I'm now based in Dublin, building towards a career in data and AI engineering in the financial services and technology sector.
Peer-Reviewed Publications
Portfolio Projects
Years Applied ML & Analytics
MSc First Class Honours
Interests
What drives me beyond the code
“The goal is to turn data into information, and information into insight.”
— Carly Fiorina
Skills & Tech Stack
The tools and technologies I work with daily
Programming
AI & Machine Learning
LLM Engineering
Data Engineering
Cloud & Big Data
Visualisation & Reporting
Projects
A showcase of my data science, AI, and ML work
Adversarially Robust XAI for Fraud Detection
Full dissertation investigating how XGBoost fraud detection models fail under adversarial attacks (FGSM, PGD, HopSkipJump) and how SHAP explanations invert under those attacks. Mapped to EU AI Act 2024 compliance.
Real-Time Fraud Detection — SWIFT/SEPA Payments
End-to-end pipeline detecting fraud in high-value cross-border SWIFT and SEPA transactions. Hybrid ML detection with SHAP-based reason codes, FastAPI serving, Kafka streaming, and live Streamlit dashboard.
AI-Powered FinTech Market Intelligence
IEEE-format research paper applying K-Means clustering, ARIMA forecasting, and country-level benchmarking to the European FinTech ecosystem. Forecasts funding stabilising at ~$241M/year.
Real-Time Big Data Streaming Pipeline
Kappa-style big data architecture for Transport Infrastructure Ireland M50 traffic data. Emulates real-time streams from CSV, ingests to Apache Kafka, processes with PySpark Structured Streaming, persists to Cassandra.
Diamond Price Prediction & Cut Classification
End-to-end data science pipeline in R on 50,000+ diamond records. Multiple linear regression (Adjusted R² = 0.9207). Cut quality classification: kNN (66%), C5.0 Decision Tree (76.14%), ANN (74.37%).
Brain Tumor Detection & Segmentation — SAM + YOLOv9 (SIYO)
A hybrid deep learning scheme integrating Meta's Segment Anything Model with YOLOv9 for automated brain tumor detection and segmentation on MRI scans. Published at IEEE ASPCC 2024, achieving 94% detection accuracy and 0.947 mAP@0.50 on the Br35H dataset.
InfraOS — AI-Native Construction Management
An AI-native SaaS platform for construction project management. Uses LangChain, LangGraph, and the Claude API to automate scheduling, risk flagging, and stakeholder reporting.
Resume
My professional journey and qualifications
Work Experience
Data & Business Analyst Intern
Aug 2024 — Nov 2024Infinite Computer Solutions · Noida, India
- ›Developed automated reporting dashboards in Power BI and Excel to support leadership reviews and governance reporting, improving reporting turnaround time by ~25%.
- ›Used SQL and Python to analyse operational and financial performance data, identifying deviations against baselines to support early risk detection and improve decision-making.
- ›Reviewed RFPs and client documentation to extract regulatory, cost, and compliance requirements, supporting structured documentation and operational control processes.
- ›Prepared stakeholder-focused presentations and structured reporting material, enabling informed business discussions and improving communication efficiency.
Data Analyst
May 2022 — Apr 2024Mount Leaf Pvt. Ltd. (Remote) · Kangra, India
- ›Analysed customer purchase patterns, product feedback, and retention metrics across 2 years of transactional data to identify high-value segments and inform marketing strategy.
- ›Built Excel and Power BI dashboards tracking acquisition rates, repeat purchase behaviour, and campaign performance, delivering actionable reporting for the leadership team.
- ›Conducted cohort and segmentation analysis to surface churn risk signals and support targeted retention campaigns.
Education
MSc Big Data Management & Analytics
Jan 2025 — Jun 2026Griffith College Dublin · Dublin, Ireland
First Class Honours (1:1 Equivalent)
Bachelor of Technology — Computer Science & Engineering
Graduated Jun 2024C.V. Raman Global University · India
First Class Distinction · CGPA: 8.50/10.00
Certifications
AWS Academy Cloud Foundations
Nov 2022Amazon Web Services
Enterprise Design Thinking Practitioner
Oct 2021IBM
Publications
Brain Tumor Detection and Segmentation using SAM Integrated YOLOv9 Scheme (SIYO)
2024IEEE ASPCC 2024 — IIIT Bhubaneswar, India
DOI: 10.1109/ASPCC62191.2024.10881978
Deep Learning-Based Tomato Plant Disease Detection using TomatoDoc Dataset
2024Springer, CIPR 2024
Volunteering
Secretary
Jan 2025 — PresentErasmus Student Network (ESN), Griffith College Dublin
Coordinating events, documentation, and cross-cultural student engagement.
Volunteer
2021 — 2024Betiya Foundation, India
Community outreach focused on education and empowerment programmes.
Blog
Thoughts on data science, ML engineering, and AI research
Adversarial Attacks on Fraud Detection: What My Thesis Found
My MSc thesis set out to answer a dangerous question: what happens to XGBoost fraud detection models and their SHAP explanations when a sophisticated adversary deliberately crafts transactions to evade detection? The answer was worse than expected.
Why SHAP Explanations Break Under Adversarial Pressure
The EU AI Act classifies fraud detection systems as high-risk AI. Article 13 requires meaningful explanations. But what if the explanations themselves can be manipulated by the same perturbation that fools the model?
SWIFT & SEPA Payments: How AI Can Catch What Rules Miss
Rule-based systems flag what they've seen before. Machine learning models catch what rules miss. But neither alone is enough for high-value cross-border payments where milliseconds and millions are both at stake. Here's how I built a hybrid detection pipeline.
Get in Touch
Whether you're a recruiter, a PhD supervisor, or building something in AI — I'd love to connect.