Open to opportunities in Japan

Dhruv Mehta

AI / Data / Cloud Engineer

AIエンジニア  ·  データエンジニア  ·  クラウドエンジニア

Building real-world systems at the intersection of LLMs, data pipelines, and cloud. Currently based in Japan — preparing for JLPT N3.

Get in Touch View Experience
scroll

01 / About

About Me

I work at the intersection of AI, data, and cloud, focusing on building practical, real-world solutions. With ~1 year of hands-on experience developing systems involving LLMs, data pipelines, OCR automation, and cloud platforms like AWS, Azure, and Databricks.

My work has included building AI-driven capacity planning systems, OCR-based evaluation tools, and implementing data governance solutions using Microsoft Purview.

Currently based in Japan, I've gained experience working in a Japanese professional environment — adapting to structured workflows, clear communication standards, and collaborative team practices. Preparing for JLPT N3.

I'm particularly interested in roles across AI, Data, and Cloud where I can contribute to solving real-world problems while continuing to grow technically and professionally.

~1yr
Professional Experience
3+
Cloud Platforms
N3
JLPT Target
JP
Based in Japan

02 / Skills

Technical Skills

AI / ML
LLMs OCR Prophet Time Series Forecasting NLP Streamlit FastAPI
Data Engineering
PySpark Databricks Azure Data Factory ETL Pipelines Microsoft Purview Data Governance
Cloud
AWS Azure AWS OpenSearch Cloud Storage Serverless
Monitoring & Tools
Grafana Tesseract Streamlit Git REST APIs Python
Languages
Python SQL HTML / CSS Japanese English
Soft Skills
Japanese Business Culture Cross-cultural Collab Documentation Structured Reporting

03 / Experience

Work Experience

Jan 2026 — Apr 2026 · Aichi, Japan
Associate Software Engineer
株式会社マップクエスト
  • Engaged with existing systems to analyze product architecture and support incremental feature improvements and issue resolution.
  • Contributed to development workflows through documentation, code understanding, and structured reporting practices.
  • Collaborated within team environments following Japanese business communication standards and review processes.
  • Built a disciplined and detail-oriented approach to work, emphasizing clarity, ownership, and continuous improvement.
  • Developed strong documentation skills, including preparing clear technical materials in both English and Japanese.
Japanese Business Documentation System Analysis
Sep 2024 — Aug 2025 · Bengaluru, India
AI, Data & Cloud Engineer
Unisys
  • Built an AI-driven capacity planning system using PySpark, Databricks, and Prophet for forecasting and optimization.
  • Developed an OCR + LLM-based evaluation system using FastAPI, Tesseract, and Streamlit for automated scoring and feedback.
  • Implemented data governance solutions using Microsoft Purview, including glossary management, metadata classification, and API-based automation.
  • Built and managed data pipelines using Azure Data Factory and cloud storage systems for large-scale data processing.
  • Performed AWS OpenSearch cost analysis and deployment planning for scalable architectures.
  • Created dashboards and monitoring systems using Grafana and Streamlit to support data-driven decision making.
PySpark Databricks Prophet FastAPI Tesseract OCR LLMs Microsoft Purview Azure Data Factory AWS OpenSearch Grafana Streamlit
Oct 2023 — Nov 2023 · Bengaluru, India
Web Developer Intern
VaultofCodes
  • Completed a four-week web development internship, working on creating responsive registration forms and debugging code errors.
  • Sharpened skills in HTML, CSS, and web development, gaining deeper understanding of front-end development practices.
HTML CSS Front-end

04 / Projects

Featured Projects

01
AI-Driven Capacity Planning System
Problem
Manual capacity planning is time-intensive and reactive, leading to resource bottlenecks and inefficiencies in enterprise environments.
Solution
Built a forecasting and optimization system using PySpark, Databricks, and Facebook's Prophet model to predict demand and automate resource planning decisions.
Impact
✓ Automated demand forecasting at scale
✓ Reduced manual planning effort significantly
✓ Enabled proactive resource allocation
PySparkDatabricksProphetAzure
02
OCR + LLM Evaluation System
Problem
Manual scoring and feedback for document-based evaluations is slow, inconsistent, and doesn't scale across large volumes of submissions.
Solution
Developed an automated evaluation pipeline combining Tesseract OCR for document extraction with LLM-based analysis, wrapped in a FastAPI backend and Streamlit UI for real-time feedback.
Impact
✓ Automated end-to-end scoring pipeline
✓ Consistent, objective feedback at scale
✓ Reduced evaluation turnaround time
TesseractFastAPILLMsStreamlit
03
Data Governance with Microsoft Purview
Problem
Large enterprises struggle with inconsistent metadata, ungoverned data assets, and lack of visibility into data lineage and classification.
Solution
Implemented an end-to-end data governance solution using Microsoft Purview, automating glossary management, metadata classification, and governance workflows via API-based automation.
Impact
✓ Standardized metadata across data assets
✓ Automated compliance classification
✓ Improved data discoverability
Microsoft PurviewAzurePythonREST APIs

05 / Certifications

Certifications

🤖
Artificial Intelligence Fundamentals
IBM / Industry Certification
☁️
Google Cloud Digital Leader – Digital Transformation with the Cloud
Google Cloud
⚙️
AWS DevOps Engineer Professional – Course Completion
Amazon Web Services

06 / Contact

Get In Touch

I'm currently open to AI, Data, and Cloud roles — especially in Japan. Whether you have a project, an opportunity, or just want to connect, feel free to reach out.

お気軽にご連絡ください。

mehtadhruv203@gmail.com LinkedIn Resume 070-9444-2193