Vardan Narula

AI Researcher

Amsterdam, North Holland, Netherlands5 yrs 9 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Expert in building AI pipelines and data models.
Proficient in Generative AI and NLP techniques.
Strong background in data engineering and visualization.

Stackforce AI infers this person is a Generative AI and Data Engineering expert in the SaaS and Fintech sectors.

Contact

Skills

Core Skills

Ai AgentsData Build Tool (dbt)Data ScienceGenerative AiNatural Language Processing (nlp)Data EngineeringData VisualizationEtl Development

Other Skills

API DevelopmentAlgorithm OptimizationAmazon Web Services (AWS)C++Data PipelinesDjangoDockerFlaskGitGoogle SheetsHuggingFaceJenkinsLangChainMATLABMicrosoft Azure

About

Started out in a classic data role, building data pipelines, automating workflows, writing heavy SQL queries, and creating dashboards ⚙️📊 These days, I’m all about GenAI, focusing on agentic development using different LLMs 🤖. I explore smart ways to plug them into real-world workflows and use NLP techniques to evaluate how well these AI agents actually perform 🔍✨

Experience

5 yrs 9 mos

Total Experience

1 yr 1 mo

Average Tenure

1 yr

Current Experience

Koalitix

AI & Data Engineer

Jun 2025 – Present · 1 yr · Rotterdam, South Holland, Netherlands · Hybrid

Building an AI pipeline for a customer to transcribe call recordings, map them to predefined categories, and score them based on brand guidelines and tone of voice. I’m acting as both the architect and primary developer, making sure the pipeline is accurate, scalable, and aligned with business objectives.
Designing and building dbt models on top of modern data warehouses to turn raw data into scalable, analytics-ready data marts for customers. I’m working as an Analytics Engineer and continually supporting fellow engineers by debugging complex SQL and dbt-related issues to ensure pipeline stability and data quality.

LangChainRetrieval-Augmented Generation (RAG)AI AgentsData Build Tool (DBT)SQLMicrosoft Azure+1

Advantech europe

Generative AI Developer

Oct 2024 – Mar 2025 · 5 mos · Eindhoven, North Brabant, Netherlands · Hybrid

Developed a RAG-powered LLM solution to automate functional test case generation and evaluation for in-house web applications, improving efficiency and coverage. Used GPT-4.0 from OpenAI Playground with LangChain for retrieval and employed CodeT5+ from Hugging Face with the BLEU metric to assess output quality.
Led the project workflow design, defined key deliverables, conducted research, performed benchmarking, and developed the product end to end.

AI AgentsOpenAI APIHuggingFaceLangChainRetrieval-Augmented Generation (RAG)Natural Language Processing (NLP)+3

Pon it

Security Data Specialist

Apr 2024 – Sep 2024 · 5 mos · Almere, Flevoland, Netherlands · On-site

Built a Snowflake data lake integrating SentinelOne and Tenable to centralize endpoint and operating system data for security managers.
Developed dashboarding pipelines using Power Query, leveraging Snowflake data and EOL API data. Created data models using DAX and built
interactive dashboards in Power BI for enhanced security insights.
Created basic Random Forest classification models to predict which OS publishers are more trustworthy.

SnowflakeAmazon Web Services (AWS)API DevelopmentMicrosoft Power BIMicrosoft Power QueryGoogle Sheets+5

Yokoy

Data Scientist

Nov 2023 – May 2025 · 1 yr 6 mos · Amsterdam, North Holland, Netherlands · Hybrid

Improved the Yokoy invoice processing feature by identifying anomalies in invoice data, such as missing fields, inconsistent formatting, and misclassified entities. Utilized the existing
OCR-model pipeline to analyze and correct these issues, enhancing the robustness of the automation system. Developed and integrated Python scripts with advanced regular expressions
to accurately extract structured information from semi-structured invoice documents, significantly improving data extraction precision and reliability.

Python (Programming Language)Regular ExpressionsData Science

Athenahealth

3 roles

Member Of Technical Staff

Nov 2021 – Aug 2023 · 1 yr 9 mos · On-site

Designed and implemented an automated ETL pipeline using Jenkins, AWS Lambdas, S3, Git, and Python to streamline the team’s monthly release process. Integrated CI/CD practices to ingest Tableau workbooks and SQL queries into Snowflake tables.
Developed a data validation automation framework using AWS S3, Lambda, and Selenium to ensure SQL-generated data on Snowflake was consistent with the Oracle data platform, maintaining data integrity, accuracy, and reliability across systems.
Worked on creating Step Functions for data pipelines on AWS, callable using Python-Django. Built an API frontend for managing Step Functions and developed a status webhook to send logs from CloudWatch to Microsoft Teams.
Created various dashboards using Power Query and Power BI with Oracle and Snowflake as data sources. Additionally, developed Tableau dashboards on Snowflake, based on requirements from Customer Success Managers, to support data-driven decision-making.
Led and majorly contributed to the initiative of integrating DBT into the ETL workflow, ingesting data from Oracle into raw tables in Snowflake, where queries created cleaned data marts and views for customer access. Developed DBT transformation files to automate processes and ensure data consistency across views.

SQLSnowflakeAmazon Web Services (AWS)Data Build Tool (DBT)DjangoAPI Development+9