Help & Supportcareers@gravityer.com
Python Engineer with less than a year in ML & Full-Stack Development
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
BCA graduate who shipped 3 end-to-end ML and mobile projects independently — spanning spam detection, geospatial fare prediction, and a full-stack Flutter app with Firebase. Writes clean Python across the stack (data pipelines → model training → prediction APIs). Ready to ship on Day 1.
Don Bosco School
10th
N/A – Present
Don Bosco College (Co-Ed), Yelagiri Hills
BCA
N/A – Present
Good Shepherd Hr. Sec. School
12th
N/A – Present
James Studio
January 1, 2026 – Present
End-to-end commercial-grade mobile app for a photography & gifting business. Designed and shipped a multi-domain mobile platform (photography + gifts) with Flutter, cutting development time by using a shared widget library across 2 business verticals. Implemented OTP-based authentication via Firebase Auth, achieving zero-credential-exposure login for all users — production security from day one. Built a real-time booking + order management system on Firebase Firestore, supporting live status updates with 0 polling — 100% event-driven architecture.
Spam Email Detection
January 1, 2026 – Present
Built a binary classification pipeline that identifies spam with measurable precision. Engineered a full NLP pipeline (tokenisation → stop-word removal → TF-IDF vectorisation), cutting feature noise by ~40% vs. raw-text baseline. Benchmarked Naïve Bayes vs. Logistic Regression; Logistic Regression achieved ~97% accuracy on the test set, outperforming the Naïve Bayes baseline by 3 percentage points. Packaged the trained model into a real-time Python prediction script that classifies a new email in <50 ms — ready to plug into any email client or API.
Uber Ride Fare Prediction
January 1, 2026 – Present
Regression system predicting ride fares from raw GPS coordinates and timestamps. Derived precise trip distance from raw lat/lon pairs using the Haversine formula, replacing noisy straight-line estimates and improving model input quality. Trained and compared 3 models (Linear Regression, Random Forest, Gradient Boosting); Gradient Boosting achieved the lowest RMSE, reducing prediction error by ~22% over the linear baseline. Evaluated rigorously with RMSE + MAE on a held-out test set, then deployed a CLI prediction script — demonstrating production-readiness beyond a Jupyter notebook.
Cultural Fit Analysis
The candidate's project portfolio demonstrates initiative and a drive for independent learning and execution. The projects are diverse, spanning machine learning and mobile development, which indicates adaptability. However, the lack of professional experience and team-based projects makes it challenging to fully assess cultural fit within a collaborative engineering environment. The target role is 'Python Engineer', and while the candidate has strong Python skills, the ML focus might require alignment with specific team needs.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive and results-oriented approach, focusing on measurable improvements and production readiness. The independent completion of multiple projects suggests strong self-management and problem-solving skills. However, without formal work experience or psychometric test results, it's difficult to fully assess team collaboration, stress handling, or broader operational fit.