Parangat Bindal

Data Engineer

Agra, Uttar Pradesh, India3 yrs 5 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Developed a chatbot using OpenAI's GPT-3.5 for organizational queries.
  • Automated ETL pipeline, enhancing data processing efficiency.
  • Engineered advanced functions for parsing complex documents.
Stackforce AI infers this person is a Data Engineer with expertise in SaaS and Generative AI.

Contact

Skills

Core Skills

Data EngineeringEtlGenerative AiSoftware DevelopmentData ProcessingData Warehousing

Other Skills

A/B TestingAADAAD AuthenticationAPI IntegrationAgile MethodologiesAlgorithmsAmazon Web Services (AWS)Analytical SkillsAnalyticsApplication Programming Interfaces (API)AutomationAzureAzure Data FactoryBack-End Web DevelopmentBusiness

About

Innovative software developer focused on generative AI. I blend technical expertise with a passion for creating impactful solutions. Driven by curiosity and continuous learning, I thrive in dynamic environments and am dedicated to delivering real-world results.

Experience

3 yrs 5 mos
Total Experience
3 yrs 5 mos
Average Tenure
3 yrs 5 mos
Current Experience

Havells india ltd

3 roles

SDE

Jul 2023Dec 2023 · 5 mos · Noida, Uttar Pradesh, India

  • Havells AI Assistance: (OpenAI GPT-3.5, Prompt Engineering, Teams SDK,Typescript, Javascript, Python, Azure,
  • Cosine Similarity, AAD Authentication)
  • Generative AI Integration: Developed a chatbot using OpenAI’s GPT-3.5 to handle organizational policy queries
  • and general questions within Microsoft Teams.
  • Advanced NLP Techniques: Implemented vector embeddings and cosine similarity algorithms to accurately compute
  • the semantic relevance of user queries, ensuring precise and contextually appropriate responses.
  • Prompt Engineering: Applied prompt engineering methodologies to enforce strict adherence to organizational
  • policies and logical boundaries within the chatbot’s responses.
  • Teams SDK and Adaptive Cards: Integrated the chatbot with Microsoft Teams using the Teams SDK and enhanced
  • the user interface with adaptive cards for a superior user experience.
  • Python Backend: Leveraged Python and various libraries for backend development, embedding processing, and
  • seamless integration.
  • Havells Intelligent Document Processor: (Camelot , PDFminer, Numpy, Pandas, Python, Azure etc.)
  • Development of Data Extraction Functions: Engineered advanced functions for parsing complex tender documents,
  • capable of systematically extracting and structuring essential information from both OCR and non-OCR files.
  • Table Removal with Camelot: Successfully integrated the Camelot library into the processing pipeline, enabling
  • the automated detection and removal of tables within PDF documents.
  • Performance Optimization: Optimized code for faster execution, including algorithmic enhancements and paral-
  • lelization.
  • Efficient CSV Generation: Developed a highly efficient and precise mechanism for the generation of CSV (Comma-
  • Separated Values) files from the extracted data.
  • Edge Case Identification: Conducted comprehensive testing and analysadais to identify and address new edge cases
  • that could potentially impact the productivity and reliability of the code.
OpenAI GPT-3.5Prompt EngineeringTeams SDKTypescriptJavascriptPython+9

Data Engineer

Jan 2023Present · 3 yrs 5 mos · Noida, Uttar Pradesh, India

  • Concur API Integration & Cost Optimization: (SQL, Python, ETL, API Integration, Data Wrangling, Data Modeling, Job
  • Scheduling, SAP, RDBMS, SSIS, SSRS, RCA)
  • ◦ Developed 15+ Python scripts to fetch 400K+ records/month from Concur APIs with 100% accuracy, eliminating manual errors.
  • ◦ Designed 18+ SQL tables & stored procedures to automate 20k+ daily SAP records, boosting retrieval speed by 40%.
  • ◦ Minimized financial discrepancies from Rs 2.5 cr/year to Rs 20-30k by correcting 98% reporting anomalies.
  • ◦ Delivered 10+ exception reports, cutting travel costs by 35% (Rs 3-4 cr annually) and improving budget control.
  • ◦ Built an automation framework to schedule 10+ SQL procedures, reducing runtime by 75%.
  • ◦ Optimized stored procedures, saving 100+ processing hours annually and enhancing pipeline efficiency.
  • ◦ Automated end-to-end ETL pipeline using Python, batch scripts, and scheduled jobs for daily system refresh.
  • Enterprise Data Migration to Databricks Lakehouse: (Databricks, PySpark, SQL Server, DLT, Azure Data Factory, ETL,
  • Python Scripting, Data Modeling )
  • ◦ Validated 600+ SQL Server tables during Databricks migration, ensuring 100% schema, volume, and data consistency.
  • ◦ Designed Databricks bronze-silver-gold Lakehouse Architecture to streamline data ingestion, transformation & advanced analytics.
  • ◦ Constructed and scheduled 20+ Delta Live Tables (DLT) pipelines for automated daily data refresh and transformation.
  • ◦ Converted 18+ Python scripts to PySpark, reducing execution time by 45% and improving cloud compatibility.
  • ◦ Mapped and ingested multi-source data using Azure Data Factory (ADF), enhancing ETL reusability and efficiency.
  • Data Modeling )
  • ◦ Engineered 4 PySpark-based anomaly detection workflows on Databricks, covering 10K+ SKUs and 20+ product categories..
  • ◦ Automated real-time data ingestion and transformation using Delta Live Tables (DLT) pipelines with 100% refresh reliability.
SQLPythonETLAPI IntegrationData WranglingData Modeling+12

Software Engineer Intern

Jan 2023Jun 2023 · 5 mos · Noida, Uttar Pradesh, India

Cvent

IT Analyst / DWH Developer

Jan 2022Jun 2022 · 5 mos · Gurugram, Haryana, India

  • Migration and Automation: Migrated stored procedures from SQL Server to Snowflake Cloud and developed
  • automated, scheduled processes using ETL tools, reducing manual effort and improving processing times.
  • Efficient performance and scalability: Optimized stored procedures, implemented UDLs/objects/views, and used
  • Snowpipe for data integration, improving run time, reducing costs, and enabling scalability.
  • Use Case Testing: Performed data pull requests and done Unit testing on various use cases.
  • Enhanced quality assurance and cost-effectiveness: Performed regular audits to ensure smooth processes, reducing
  • manual work, increasing cost-effectiveness, and preventing potential issues.
SQL ServerSnowflake CloudETL toolsUDLsobjectsviews+3

Education

Indian Institute of Information Technology(IIIT), Sonepat

intermediate — Information Technology

Jan 2019Jan 2023

ST Andrews public school , agra

science

Jan 2017Jan 2018

Stackforce found 100+ more professionals with Data Engineering & Etl

Explore similar profiles based on matching skills and experience