Chirag Bhutada

Product Engineer

Pune, Maharashtra, India2 yrs 8 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Developed AI-driven metadata pipeline for restaurants.
Achieved 97% accuracy in ML model classification.
Optimized PostgreSQL performance by 50%.

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

Contact

Skills

Core Skills

Data EngineeringAiMachine LearningDatabase Management

Other Skills

Google Places APIGPT-4Perplexity APIsDomoPythonRetrieval-Augmented Generation (RAG)Azure Data FactoryEvent HubsDatabricksDelta LakeXGBoostRandom ForestAutoencodersPostgreSQLPySpark

About

Master’s student in Data Science at Manchester Metropolitan University with strong expertise in AI and data engineering Experienced in developing multimodal Retrieval-Augmented Generation (RAG) systems integrating text, images, and structured data for enhanced contextual insights Skilled in PySpark optimization for high-volume data processing and performance tuning Proficient in building automated ETL workflows and scalable data pipelines using Azure Data Factory and Databricks Implemented workflow automation in DOMO, streamlining reporting and operational processes to reduce manual effort Optimized PostgreSQL performance by 50% through advanced indexing and query tuning Automated CI/CD pipelines with Azure DevOps, enabling real-time and reliable data synchronization across enterprise systems Passionate about delivering scalable, efficient, and production-ready AI-powered data solutions

Experience

2 yrs 8 mos

Total Experience

10 mos

Average Tenure

1 yr

Current Experience

Manzeera solutions

AI Data Engineer

Jun 2025 – Present · 1 yr · United Kingdom · Remote

Developed an AI-driven metadata pipeline for 1,500+ UK restaurants using Google Places API, GPT-4, and Perplexity APIs, with fallback LLM fine-tuning and prompt-engineering logic to improve data completeness and contextual accuracy.
Automated Domo Webform ingestion with user-triggered workflows, reducing data duplication by 40% and ensuring row-level traceability across restaurant datasets.
Implemented Magic ETL and SQL ranking logic for deduplication, freshness scoring, and prioritization, enabling reliable, high-quality metadata curation.
Engineered reusable Python modules in Domo Code Engine with Azure Blob Storage for scalable ingestion, storage, and processing of structured restaurant metadata.
Applied Retrieval-Augmented Generation (RAG) to query metadata and APIs, enriching missing fields (e.g., owner details, cuisine type, contact info) and ensuring higher accuracy and consistency.
Integrated NanoBanana API to generate AI-powered images for menu items, enhancing dataset completeness and enabling realistic visual representation of restaurant offerings.
Designed a hybrid AI orchestration pipeline combining RAG-based enrichment, API-driven location intelligence, fine-tuned LLM reasoning, and image generation to streamline restaurant discovery, menu creation, and content pipelines.

Google Places APIGPT-4Perplexity APIsDomoPythonRetrieval-Augmented Generation (RAG)+2

The manchester metropolitan university

Data Engineer

Oct 2024 – May 2025 · 7 mos · Manchester, England, United Kingdom · Hybrid

Extracted and ingested ~1M IIoT logs, 500K phishing emails, and 300K malicious URLs using Azure Data Factory, Event Hubs, and Databricks (PySpark) for centralized processing and analysis.
Stored processed data in Delta Lake to enable efficient querying and support downstream machine learning workflows for anomaly detection.
Developed and deployed ML models (XGBoost, Random Forest, Autoencoders) via Azure ML, achieving up to 97% classification accuracy on test datasets.
Created interactive Dash dashboards to present near real-time detection insights, model performance metrics, and data trends to stakeholders.
Integrated a GPT-4 powered AI chatbot with RAG capabilities to retrieve relevant knowledge base articles and recommended remediation steps based on detected patterns in the data.

Azure Data FactoryEvent HubsDatabricksDelta LakeXGBoostRandom Forest+4

Bajaj finserv

2 roles

Data Engineer

Jul 2023 – Aug 2024 · 1 yr 1 mo · On-site

Designed and optimized 20+ PostgreSQL functions, procedures, and relational tables, improving query performance by 50% through indexing, execution plan tuning, and SQL optimization.
Built batch and incremental ETL pipelines in Azure Data Factory with PySpark for data transformation, deduplication, and aggregation across 100K+ master data records, reducing redundancy by 40%.
Integrated PySpark for complex joins, aggregations, and business-rule-based transformations, enabling faster processing of high-volume datasets.
Automated CI/CD workflows for PostgreSQL and ETL deployments using Azure DevOps, Git, and Azure Key Vault, reducing deployment errors by 70%.
Developed monitoring scripts in Python for pipeline health checks and auto-recovery, ensuring high availability across 10+ enterprise systems.

PostgreSQLAzure Data FactoryPySparkAzure DevOpsGitPython+2

Data Engineer intern

Jan 2023 – Jul 2023 · 6 mos · On-site

Acquired in-depth knowledge of PostgreSQL, expanding skills in database development and optimization during a dynamic and impactful internship.
Engineered and optimized sophisticated data structures to support efficient interactions, thereby enhancing system performance and responsiveness.
Developed a database backend for various product-on-demand applications used within the organization, ensuring real-time use and quick responses.
Aligned closely with the front-end team to integrate database functionalities seamlessly with user interface requirements, contributing to creating a cohesive and intuitive customer experience.

PostgreSQLDatabase DevelopmentDatabase Management