Sagandeep Kaur

Next.js, React, TypeScript, FastAPI, PostgreSQL, Redis, Celery, PyTorch, OpenCV, Docker

• Team-built defect-detection platform supporting image annotation, synthetic defect generation, MobileNetV3 training with real-time progress, inference runs, team permissions, and automated defect reports.
• Contributed as a team member rather than owner: 22 public commits covering UI, model and image views, account flows, navigation, and chatbot rendering.

Python, Streamlit, FAISS, SQLite, Scikit-learn, Plotly, Ollama (optional), Docker

• Built a multi-page procurement dashboard for document upload, cited AI question answering, delay prediction, vendor risk, and alerts.
• Implemented local RAG with document chunking, HashingVectorizer embeddings, FAISS retrieval, SQLite persistence, and grounded-answer fallbacks.
• Developed Random Forest delay-risk scoring, vendor reliability ranking, schedule-impact alerts, synthetic demo data, tests, and a reproducible Docker image.

Python, Flask, SQLAlchemy, SQLite, Jinja, Bootstrap, Chart.js, Docker

• Built a standalone dashboard for latest-year LC activity, historical trends, and chapter-level timelines.
• Added validated CSV ingestion with upserts, JSON analytics endpoints, and inactive-chapter export.
• Published synthetic sample data and clearly separated this showcase from NPTEL's production Local Chapter systems.

Python, PyTorch, ResUNet, GAN, OpenCV, NumPy, Pandas, Matplotlib, Kaggle GPU

• Built a cloud-removal pipeline mapping cloudy optical imagery and masks to reconstructed cloud-free satellite outputs.
• Prepared RICE1/RICE2 manifests, trained a mask-guided ResUNet with cloud-aware L1 and SSIM loss, and exported visual predictions.
• Reached about 22.74 dB PSNR and 0.796 SSIM on RICE2 testing, then explored GAN refinement and Bhoonidhi LISS-IV data automation.

Python, PyTorch, Hugging Face, Whisper, Faster-Whisper, Indic Conformer, Librosa, Torchaudio, Kaggle

• Built an English, Hindi, and Tamil transcription pipeline for a Kaggle speech recognition challenge.
• Added language identification and dynamic model routing across Whisper large-v3-turbo and Indic Conformer models.
• Implemented transcript normalization, WER evaluation, beam-search inference, FP16 GPU execution, caching, and Kaggle submission generation.
• Placed 22nd of 190 teams on the Kaggle public leaderboard with a best WER of 0.221.

Python, Hugging Face Transformers, Gemma, LoRA, PEFT, bitsandbytes

• Fine-tuned google/gemma-3-1b-it with LoRA/PEFT for binary sentiment classification across 13 Indian languages.
• Built preprocessing, label encoding, tokenization, training, validation, diagnostics, and Kaggle submission workflows.
• Used memory-efficient training with bitsandbytes and Hugging Face Trainer, scoring 0.9756 public / 0.9655 private on Kaggle (rank 41 of 209, public leaderboard).

Python, PyTorch, NumPy, Pandas, PIL, Matplotlib, Seaborn, U-Net, PixelShuffle, CUDA

• Built a PyTorch restoration pipeline for the RELLISUR/Kaggle dataset with denoising, illumination correction, and 4x super-resolution.
• Designed a custom SR U-Net with encoder-decoder blocks, skip connections, PixelShuffle upscaling, and refinement layers.
• Reduced public RMSE from a 41.8 baseline to 18.71 (best private 16.65) using EDA-driven modeling, loss tuning, mixed precision, TTA, and calibration; rank 14 of 175 on the public leaderboard.

Python, PyTorch, U-Net, NAFNet, NumPy, Pandas, Matplotlib, Kaggle GPU

• Restored clean 32x32 RGB images from corrupted inputs, progressing from a Gaussian-blur baseline through a residual CNN and U-Net to a NAFNet with bottleneck attention.
• Trained the final NAFNet on a deadline-aware ~5 h Tesla T4 schedule with test-time augmentation.
• Best MSE 32.30 public / 32.58 private against a pass threshold of 180, rank 9 of 96 teams on the public leaderboard.

Python, Scikit-learn, MLflow, DVC, GCS, Feast, BigQuery, FastAPI, Docker, GKE, OpenTelemetry

• Built an Iris classification pipeline with cloud artifact storage, data versioning, feature store setup, and experiment tracking.
• Automated CI/CD with GitHub Actions, pytest, CML reports, Dockerized FastAPI serving, Kubernetes deployment, HPA, and load testing.
• Added model explainability, fairness checks, drift monitoring, guardrails, and LLMOps/MLSecOps experiments.

Python, FAISS, Streamlit, Gemini, NLP chunking, semantic embeddings

• Built a local RAG system that synthesizes grounded answers from proprietary documents with refusal behavior for unsupported queries.
• Optimized CPU-bound vector similarity search with FAISS flat L2 indexing and overlapping text chunking.
• Created a Streamlit dashboard for PDF ingestion, session-state memory, constrained Gemini prompting, and citation-aware responses.

Python, Scikit-learn, LightGBM, XGBoost, Pandas, Matplotlib

• Built a classification model to predict system vulnerabilities.
• Implemented preprocessing, evaluation, and model performance analysis.
• Benchmarked 45 model iterations across linear, SVM, tree-based, boosting, MLP, and ensemble models; tuned LightGBM reached the best Kaggle accuracy of 0.63270.

Vue.js, JWT, Celery, Redis, Mailhog

• Built a full-stack application with admin, customer, and professional roles.
• Developed APIs, authentication, async task handling, and workflow automation.

Flask, SQLite, Python

• Designed database schema and REST APIs for campaign and user data handling.
• Built backend flows to connect brands with influencers.

Python, Pandas, Excel, Matplotlib, Seaborn, SQLite, Flask

• Analyzed sales and customer data to identify trends and improve inventory decisions.
• Created visualizations to communicate insights clearly.