struct ContentView: View {
@State var predictions: [MLResult]
var body: some View {
ScrollView {
LazyVGrid(columns) {
ForEach(predictions)
}
}
}
}
import torch
from transformers import AutoModel
class SentimentNet(nn.Module):
def forward(self, x):
h = self.encoder(x)
return self.classifier(h)
Hello! Im Manikanta Sirumalla, an iOS Engineer with 3+ years in Swift, SwiftUI, and UIKit, building polished mobile experiences with practical data intelligence
About
I bring a hybrid profile across iOS engineering and data science, with a strong focus on product outcomes. Over the last 3+ years, I have worked on real-world mobile applications from idea to release, handled production issues, improved performance, and built features that directly improve user engagement. Alongside engineering, I am pursuing my Master's in Data Science at UMBC to design smarter product experiences using practical machine learning.
I have hands-on experience delivering iOS apps across different domains, including feature ownership, bug fixing, release cycles, and continuous improvements after launch. My work spans architecture planning, API integration, offline-first flows, testing, and performance tuning. I build with Swift, SwiftUI, UIKit, CoreData, CloudKit, and Firebase, and follow production-ready patterns like MVVM to keep codebases scalable and maintainable.
In parallel, I build practical data and ML solutions using Python, SQL, Scikit-Learn, TensorFlow, and PyTorch. My experience includes predictive modeling, anomaly detection, and analytics pipelines. I focus on bringing this intelligence into product workflows in ways that are clear and actionable, whether through recommendations, smarter prioritization, or insight-driven features that improve decision-making for users and teams.
Expertise
Elegant, performant native apps
From notebooks to insights
Selected Work
From concept to production — organized by domain.
Production iOS fitness platform for workout tracking, AI-powered plan generation, streak intelligence, HealthKit sync, and rich progress analytics with exportable reports.
On-device multi-modal skin lesion classification app with camera/library scan, 3D body-location mapping, Grad-CAM interpretability, confidence gauges, and lesion learning workflows.
Multi-category news app with trending and keyword search, bookmarks, sharing, and custom animated tab bar. Integrated Firebase for auth and Firestore for real-time data.
AI-powered iOS app exploring creative possibilities with intelligent features and polished native UI.
Photography and storytelling app with beautiful image presentation and narrative features.
Clean, functional calculator app with elegant UI design and smooth interactions built in pure Swift.
Enterprise-grade Big Data analytics platform analyzing tech job market trends, salary predictions, and skill demand forecasting. Processed 129.68 GB across 4 data sources using distributed computing with a 3-layer Data Lake architecture (Raw → Bronze → Silver → Gold) and 2.7M+ records.
End-to-end enterprise fraud detection system with a complete data pipeline from ETL to interactive dashboard. Designed a normalized 7-table database schema, engineered 35 features across 7 categories, and deployed an Isolation Forest model processing 1,597 expense claims across 467 employees and 15 departments.
Comprehensive ML solution for telecom customer retention — engineered 40+ features and benchmarked 7+ algorithms (Logistic Regression, Random Forest, XGBoost, Gradient Boosting, SVM, KNN, Neural Networks) with GridSearchCV hyperparameter tuning and SHAP-based model interpretation for actionable business insights.
Predictive ML model analyzing academic profiles, research experience, and test scores to forecast graduate admissions probability with high accuracy.
Quantitative trading signal analysis using statistical modeling and ML pattern recognition to identify profitable market trends from historical data.
Experience
Deepening expertise in machine learning, statistical analysis, Python, R, SQL, and data-driven decision making. Working on academic ML projects including graduate admissions prediction and trading trend analysis.
Led iOS app development using MVC, MVVM, and Delegate patterns, improving architecture and maintainability. Optimized API requests cutting data retrieval time by 30%, increased user engagement by 20% via interactive SwiftUI animations, and implemented Codable-based JSON parsing reducing data processing time by 50%.
Developed new mobile apps across the full lifecycle. Collaborated with a cross-functional team on UI/UX design, API integration, and Git workflows. Gained deep experience with Swift, Xcode, generics, and code optimization.
Contributed to enterprise applications focused on performance and scalability. Worked in cross-functional teams to deliver client solutions and applied testing tools including Selenium.
Testimonials
"Manikanta consistently delivered clean, well-architected iOS code that was easy to maintain and extend. His SwiftUI animations boosted user engagement by 20%, and his API optimizations cut data retrieval time by 30%. A reliable, detail-oriented engineer."
Manikanta picked up our full development workflow remarkably fast during his internship. He was shipping production-quality features by week three and his code reviews were consistently thorough.
His ability to combine iOS expertise with a strong data science foundation makes him stand out. The ML projects he's built in our program show real engineering maturity — not just notebooks, but clean, reproducible pipelines.
Great team player who brings a solutions-first mindset. He localized our apps for multiple regions flawlessly and reduced code duplication by 30% with smart use of generics. Highly recommended.
Publications
Contact
Looking for an iOS developer with a data science edge? I'm in Baltimore, MD and available for full-time or remote work.