Parva Patel
Open to work0 years experienceSoftware Engineer
Software Engineer and AI/ML Specialist with expertise in data pipelines, LLMs, and business intelligence.
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
31 skillsGitHub Activity Evidence
GitHub Footprint Not Connected
Recruiters value verified code contributions. Linking a GitHub account displays live heatmaps, active contribution metrics, repository languages, and push activity tags.
Work Experience
Software Engineer
MAQ Software
- Designed and developed scalable backend services and enterprise-grade applications using Python for Microsoft ecosystem solutions.
- Built robust data processing pipelines to transform, validate, and analyze large volumes of structured and unstructured customer feedback data.
Associate Software Developer
MAQ Software
- Architected robust backend microservices to process and analyze conversational chatbot feedback for a Microsoft 365 product comparison portal.
- Implemented sophisticated data-cleaning and dataset-generation pipelines utilizing Python to extract sentiment and intent from unstructured customer conversations.
- Streamlined the chatbot feedback pipeline by generating structured datasets that improved response quality and user engagement.
Projects
Enterprise Retail Intelligence & Demand Forecasting Platform
- Architected an end-to-end Lakehouse solution in Microsoft Fabric to ingest, orchestrate, and transform 50M+ rows of multi-source retail transactional data using Fabric Data Factory pipelines into delta tables.
- Developed scalable machine learning models using PySpark and SynapseML within Fabric Notebooks to predict inventory demand thresholds and seasonal consumer purchasing patterns with a 94% forecasting accuracy.
- Engineered executive-level Power BI dashboards utilizing DirectLake mode to visualize revenue performance, supply chain anomalies, and predictive stockouts, significantly reducing report rendering latency.
- Implemented advanced DAX measures to calculate dynamic time-intelligence KPIs, enabling stakeholders to run real-time what-if simulations for pricing optimizations.
Advanced Hate Speech Detection via NLP
- Developed a highly accurate hate speech classification model by processing and analyzing a customized 20,000+ sample social media dataset.
- Upgraded traditional ML approaches (KNN, Decision Trees) by implementing advanced NLP architectures, including FastText embeddings and Transformer models (BERT/DeBERTa), significantly improving contextual understanding.
- Applied advanced tokenization, stemming, and vectorization techniques to clean noisy text data.
Telecom Customer Churn Predictive Modeling
- Led comprehensive Exploratory Data Analysis (EDA) on a 7,000+ customer dataset to uncover hidden churn patterns and demographic correlations.
- Engineered predictive features from raw data, handling missing values and ensuring rigorous data consistency.
- Identified critical business risks (e.g., month-to-month contracts, electronic checks) and presented data-backed retention strategies through intuitive visualizations.
Multi-Class Digit Recognizer (MNIST)
- Architected and trained a feed-forward neural network to achieve high-accuracy multi-class classification utilizing a Softmax output layer.
- Demonstrated deep algorithmic understanding by independently coding a neural network from scratch, encompassing forward propagation, backpropagation, and gradient descent.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Diploma in Multilingual Computer Programming
Diploma in Multilingual Computer Programming (Grade A+) — C-DAC
Certificate of Scholar
Maintained SGPA of 8.50+ across multiple academic semesters.
Community Service Excellence
Awarded for dedicated volunteer contributions and impactful community engagement.
About Details
Professional Bio
Results-driven Software Engineer and AI/ML Specialist with a strong foundation in Computer Science, Cyber Security, and Enterprise Data Analytics. Expertise in architecting end-to-end data pipelines, training Large Language Models (LLMs), and implementing scalable business intelligence solutions.
B.Tech. in Computer Science & Engineering (Minor: Cyber Security) in Computer Science & Engineering
Institute of Technology, Nirma University (2022 - 2026)