Sriharsan BS
Production ML that turns messy data into decisions!!
New to Contra
Sriharsan is ready for their next project!
Day one on Contra. New to the platform, not to the work.
I build production ML systems that turn messy data into decisions, and I build the product around them.
Where I am strongest:
Production ML: risk scoring, prediction, ranking, computer vision
Data engineering: pipelines that turn raw, scattered data into reliable features
LLM apps: RAG, structured prompting, and evaluation that keeps them honest
And I built the full product around it, too: FastAPI and backend services, React and Next.js frontends, dashboards, mobile, and workflow automation when a project needs it. I like owning the whole path from data to a working thing people use.
Most builders stop at the demo. I take it to be deployed, monitored, and actually earning its keep.
I also provide automation services for your Saas that you don't wanna waste your hours on.
Starting today, I am open to work. Independent contracts, remote, a full build, or one piece of one. Startups and small teams turning an idea into a real product are exactly who I want to work with.
My projects are on my profile if you want to see how I think before we talk.
A piece of my playground work done within hours is posted too.
#MachineLearning #AIEngineer #LLM #FastAPI #React #Nextjs #Contra
1
7
NeuroVision AI is a clinical-grade platform that detects neurological gait disorders from walking videos using computer vision and AI. It extracts key biomechanical parameters - cadence, symmetry, tremor index, and freezing episodes, via MediaPipe pose estimation and Isolation Forest anomaly detection, trained on established datasets including DaphNet and PhysioNet GaitPDB. The system delivers AI-powered differential diagnoses, real-time clinical Q&A, and spoken voice reports, all within 60 seconds of video input.
0
20
TechnovaHub chatbot is a branded AI-powered customer assistant built with React and Node.js, featuring real-time streaming responses via Google Gemini API. It supports bilingual interaction (English and Tamil), voice input, lead capture, and smart intent detection for courses and pricing. The chatbot includes a secure backend proxy, XSS sanitization, and a modular architecture with 57 automated tests ensuring production-grade reliability.
1
24
VitalFlow HeartGuard is a cardiovascular risk analytics platform built on the Framingham Heart Study dataset (4,238 patients). It trains three Apache Spark ML models — Logistic Regression, Random Forest, and Gradient Boosted Trees — to predict 10-year coronary heart disease risk. The platform features a FastAPI backend with JWT auth, live what-if analysis, counterfactual interventions, model drift detection, and PDF report generation. A React dashboard visualizes EDA, ROC curves, feature importance, and patient risk trends.
0
26