Soumya Zacharia

AI Development & Implementation: Integrated AI capabilities into our platforms core to automate time-consuming supply chain tasks. This
•
included document parsing, invoice reconciliation, key information detection, automatic order creation, message reply suggestions, and document
tagging, directly addressing the challenge of manual data entry and verification. The solution resolved key user pain points, slashing manual input
by 80% and significantly streamlining workflows.
Implemented a customer data and platform-focused chatbot using cutting-edge LLM techniques, enhancing the end-to-end supply chain platform
user experience by enabling users to quickly retrieve specific shipment information without navigating through all their data.
Data Engineering & Business Intelligence: Architected robust data pipelines using Cloud SQL and BigQuery to process and analyse last mile
delivery app data, reducing accounting reconciliation time by 70%.
Utilized advanced SQL techniques, including complex joins and blends, to deliver insightful reports and visualizations that enabled faster, more
accurate logistics decisions for customers regarding their shipments and purchase orders
Software Development & Feature Design: Played a key role in the backend development of end to end supply chain dashboard, including
database modeling, API creations, cloud deployment and writing end-to-end test scripts, ensuring scalable and maintainable code.
Built a comprehensive WhatsApp chatbot using Twilio, and Dialogflow, improving user engagement and decreasing customer support time for
order status inquiries by 40%.
Developed core modules of the last-mile delivery application, implementing custom APIs and managing PostgreSQL backends for reliable data
integration and performance, with Continuous Integration and Continuous Deployment (CI/CD) pipelines established using Git and GCP.
Actively contributed feature ideas and enhancements to improve user experience and platform functionality, conducted peer code reviews, and
addressed bugs efficiently to maintain production stability

Developed parallel processing analytic pipelines using Python, R and Linux to preprocess high throughput DNA sequencing files to analyse the distribution patterns in cancer vs. healthy samples and perform other statistical analyses in support of lab-based and collaborative research.
Utilized advanced Bioinformatics tools and predictive modelling using Ridge Regression and other MLAlgorithms to develop classification model,
aiming at early Cancer detection using less invasive methods.
Designed workflows using Python to detect mutational signature patterns, identify samples with high deletion or duplication in DNA sequences
(microsatellite instability), and study the association with genotypic, phenotypic factors and response to medications, using statistical and
visualization techniques.
Collaborated with external Researchers and Scientists on multiple genomic projects by providing analytic assistance, interpretation, and
presentation of results.
Contributed to research works published in leading Medical Journals.

Developed scalable and reproducible pipeline for Genome Analysis using Python to generate summary plots, perform association tests and detect data anomalies and created webpage to view outputs using Jinja2 template.
• Designed Tableau dashboards and performed statistical tests (Hypothesis tests, regression) to analyse the overlap between COPD and Asthma condition, using the clinical study data of 3000 patients.
• Created reference catalog mapping variants to gene information from datasets of over 30M rows using R Studio, reducing decision making time for end users.
• Prepared and transformed clinical data to perform regression analysis and examined the relationship between the gene information and phenotypes, with 93% accuracy using Python.
• Improved the efficiency of the file search system by using the Natural Language Processing and Image Processing techniques to automatically retrieve information from the research manuscripts, reducing the data entry time from 20 mins to less than 4 mins.

Utilized optimized SQL queries for inserting, manipulating, retrieving data and for testing APIs, reducing task completion time by 40%.

Served as the team leader for testing portal application and CRM software.
Created operational excellence dashboards using Excel to efficiently prioritize tasks and monitor the progress of the team, improving the delivery
of backlog by 25%.
Comprehensive knowledge of Agile Software Development Life Cycle and collaborated with multiple teams to layout test strategies.