AI/ML Engineer - Document Processing & Automation Expert

Anand Dhone

Bengaluru, India • 770-***-**** • **********@*****.***

Results-driven AI/ML Engineer specializing in intelligent data processing solutions utilizing Python, Machine Learning, and Large Language Models. Skilled in developing document AI pipelines and extracting structured data from unstructured PDFs. Expertise in data preprocessing, feature engineering, and predictive analytics with tools such as Pandas and Scikit-learn. Capable of designing scalable data pipelines and building APIs to enhance operational efficiency.

Experience

Aug 2025 – Feb 2026

Sr AI ML Engineer L1 Publics Sapient (Nelson) Bengaluru, India Project: UK Custom OCR

Python-based invoice data extraction system to convert unstructured PDF invoices into structured JSON. Designed regex and label-based extraction logic to handle multiple invoice formats and normalize vendor-specific labels into standardized data fields. Integrated extraction pipeline with Django-based API to process uploaded invoices, delivering structured JSON responses.

Project: Vendor Onboarding

An in-house OCR and LLM-based document processing solution using Python, Tesseract OCR, and PyMuPDF to extract text from uploaded PDF attachments and transform it into structured JSON. Integrated Azure OpenAI (LLM) to intelligently parse and extract key business fields. The solution was exposed through internal REST APIs to support automated vendor onboarding workflows and integrated with external Altair APIs for authorization and vendor request creation, enabling scalable and automated document data extraction. Project: Legal (Billing Consolidation & Reconciliation System) Designed an AI-powered data consolidation pipeline using Python and Pandas to process and standardize multi-source Excel billing reports into a unified financial dataset. Implemented an LLM-based schema mapping solution using LangChain and Azure OpenAI, enabling automated header mapping and integration of heterogeneous Excel sheets with minimal manual intervention.

Jan 2023 - Mar 2024

Sr AR Associate (Healthcare Data Analytics) Kraft BPO Solution Pvt Ltd Bengaluru, India Developed machine learning pipeline for predicting healthcare claim denials using historical AR datasets. Processed healthcare claim data with Python and Pandas, ensuring thorough data cleaning and transformation. Engineered predictive features from claim attributes, including service date and denial indicators. Created target variable for classifying claims as denied or approved, enhancing model accuracy. Applied label encoding for categorical feature transformation. Developed Power BI dashboards to visualize AR trends, denial rates, and payer performance. Dec 2020 - Apr 2022

Customer Support Data Analyst (Grade L1.2) Genisys Group Bengaluru, India Spearheaded data analytics initiative to analyze customer service CRM case data. Processed unstructured and semi- structured customer interaction data from Salesforce CRM into structured analytical datasets. Conducted Exploratory Data Analysis (EDA) to identify complaint patterns and escalation frequencies. Performed data preprocessing including data cleaning and feature structuring of attributes such as issue category, vehicle model, service location, and resolution time.

Jan 2020 - Oct 2020

Sr AR Data Analyst ACN Healthcare RCM Service Pvt Ltd Bengaluru, India Analyzed healthcare claims and AR datasets to identify denial trends, leading to enhanced reimbursement cycles. Worked with structured healthcare claim data including patient demographics, CPT codes, insurance coverage, billed amounts, and payer responses. Conducted denial root cause analysis by reviewing Explanation of Benefits (EOB) and Remittance Advice (RA). Partnered with RCM teams to resolve complex claim denials, contributing to increased revenue recovery. Built operational dashboards using Power BI to monitor denial trends and collection performance. Applied Excel analytical techniques including Pivot Tables, lookup functions, filters, and data validation. Mar 2017 - Aug 2019

AR Data Analyst Ascent Business Solutions Pvt Ltd Nagpur, India Analyzed Accounts Receivable (AR) datasets to identify claim denial trends and improve claim recovery rates. Collaborated with the Revenue Cycle Management team to identify denial root causes and improve claim submission accuracy. Processed structured healthcare claims datasets, including invoice numbers and denial codes, to support data-driven decision making. Applied Excel analysis techniques, including Pivot Tables and formulas, to enhance data accuracy and insights. Maintained claim tracking datasets and operational reports for monitoring appeals and claim resolution efficiency.

Internship

Dec 2020 – Jun 2021

Data Science Intern FlipRobo Technologies Bengaluru, India

• Performed web scraping and data extraction using Python libraries such as Beautiful Soup and Selenium to collect structured data from websites.

• Implemented Selenium automation workflows and handled common Selenium exceptions to improve automation reliability and troubleshooting.

• Conducted COVID-19 data analysis for the United States, analyzing case growth, vaccination rates, and regional trends using data-driven techniques.

• Applied Python (Pandas, NumPy), SQL, and Exploratory Data Analysis (EDA) to clean, process, and analyze large datasets.

• Built predictive models using Machine Learning techniques (Regression) to analyze infection trends and evaluate policy impacts.

• Developed data visualizations and dashboards to present insights using Python visualization libraries and Power BI.

• Performed HR analytics on employee datasets, identifying patterns in workforce performance, attrition rates, and operational trends using Python, SQL, and Power BI.

• Built a classification model using Scikit-learn to predict passenger survival probabilities based on demographic and ticket information, applying feature engineering and EDA to improve model performance. Education

DEC 2020

PG Program In Data Science, Machine Learning from Data Trained Education Bengaluru, India MAY 2019

Masters in Computer Management Nagpur University Nagpur, India 7.9 GPA • Secured 2nd Rank in Intercollege Stock market Competition DEC 2015

Bachelor of Commerce in Computer Application Nagpur University Nagpur, India 5.5 GPA • Academic Project selected for presentation at an Intercollege Competition MARCH 2011

12th Commerce Nagpur University Nagpur, India

6.1 GPA • Secured 2nd Rank in Accountancy

Certifications

• Learning Data Analytics: 1 Foundations from LinkedIn Learning Skills

• Programming Languages: Python, SQL

• Data Science & Machine Learning: Scikit-learn, TensorFlow, PyTorch, Pandas, NumPy

• Natural Language Processing (NLP): Sentiment Analysis

• Data Visualization: Power BI, Matplotlib, Seaborn, Plotly

• Data Manipulation: DataFrames (Pandas), Excel (Advanced), Power Query

• Artificial Intelligence & Generative AI: Azure OpenAI, Large Language Models (LLMs), LangChain, Prompt Engineering

• OCR & Document Processing: Tesseract OCR, PyMuPDF, pdfplumber, Regex-based Data Extraction, Document Data Structuring

Contact this candidate