Skip to main content
MariaBerchmans UserMU
Looking for a job

MariaBerchmans User

@mariaberchmansuser

Senior data scientist in AI and financial services, with a PySpark entity resolution pipeline that cut duplicate records from ~18% to <2%.

United Arab Emirates
Message

At JLL, I built a PySpark entity resolution pipeline for JLL Azara that standardized 25,000+ multilingual company-name records. It reduced the duplicate entity rate from ~18% to <2% and saved ~3–4 person-weeks per refresh cycle.

At JLL, I also developed modules for a commercial lease-renewal scoring pipeline, using XGBoost to flag at-risk leases up to 18 months before expiry. The classifier achieved an AUC of 0.80, and its predictions fed a downstream NPV optimization engine.

In my independent AI research, I fine-tuned AraBERT for Arabic dialect identification, achieving 86% macro-F1 across 26 city-level labels. I also built FinTrace, a financial question-answering system that achieved 96.66% Hit@1 for evidence ranking, and a multi-agent RAG system for SEC financial disclosures.

Experience

Work history, roles, and key accomplishments

IR
Current

Independent Research & AI Specialisation

Independent Research

Jul 2025 - Present (1 year 4 months)

Actively deepening expertise through hands-on research projects in AI, NLP and multi-agent systems, including Arabic dialect identification, financial document question answering and enterprise data intelligence agents.

AINLPMulti Agent Systems
Dialect Identification and Labeling
Document QA
Data Intelligence
JLL (Jones Lang LaSalle) logoJL

Senior Analyst — Data Management & Delivery

Jul 2021 - Jan 2023 (1 year 6 months)

Developed modules of a scoring pipeline to predict commercial lease renewals and post-expiry vacancy duration, training an XGBoost classifier achieving AUC 0.80 and Brier Score 0.124.

PythonXGBoostscikit learn
Isotonic Regression
LIFELINE
Databricks Feature Store
Delta LakeMLFlowPandas
BM

Senior Analyst — Data Management & Quantitative Analysis

Apr 2016 - Jun 2018 (2 years 2 months)

Worked on allocation, capital-flow and performance analysis for institutional pension plans, developing multiple-regression models forecasting asset-allocation trends with R2 of 0.78-0.84.

L&T Infotech logoLI

Software Engineer — ETL & Risk Data Validation

L&T Infotech

Sep 2013 - Feb 2016 (2 years 5 months)

Validated Informatica ETL pipelines and developed SQL queries for source-to-target reconciliation and risk-reporting discrepancy analysis, supporting reliable Basel II risk reporting.

Education

Degrees, certifications, and relevant coursework

Microsoft logoMI

Microsoft

Microsoft AI-300: MLOps Engineer Associate, MLOps

Earned the Microsoft AI-300: MLOps Engineer Associate certification in October 2026.

Great Learning logoGL

Great Learning

Generative AI for NLP, Generative AI for NLP

Completed the Generative AI for NLP certification from Great Learning in April 2025.

Great Lakes Institute of Management logoGM

Great Lakes Institute of Management

PG Program, Business Analytics

Completed a PG Program in Business Analytics from Great Lakes Institute of Management in January 2017.

Sathyabama University logoSU

Sathyabama University

Bachelor of Engineering, Electronics & Communication

Grade: 81%

Earned a Bachelor of Engineering in Electronics & Communication from Sathyabama University with 81% in January 2013.

Interested in hiring MariaBerchmans?

You can contact MariaBerchmans and 600K+ other talented remote workers on Himalayas.

Message MariaBerchmans

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan