For students
Pick a brief below, or bring the problem statement your department handed you. We architect it with you, review every commit, deploy it to a real URL, and rehearse the viva until no question surprises you.
See student support4 scoped briefs
2 mini · 2 major
Deep learning projects fail for boring reasons: a bad split, an untracked experiment, a metric that flatters the model. We build with proper experiment tracking, augmentation, and a held-out set nobody touches — so the number you report is the number a reviewer can reproduce.
Two audiences, one engineering standard
Pick a brief below, or bring the problem statement your department handed you. We architect it with you, review every commit, deploy it to a real URL, and rehearse the viva until no question surprises you.
See student supportComputer vision for inspection and quality control, OCR and document understanding, audio models, and fine-tuning open-weight models on your own data.
Discuss a company buildMini projects
Three to four weeks. Narrow enough to finish, deep enough that you learn the decision that actually matters.
Classify scans with augmentation, class-imbalance handling, and Grad-CAM heatmaps that show what the model looked at.
You walk away with
A YOLO-based detector running live on a webcam feed, quantised so it holds frame rate on ordinary hardware.
You walk away with
Major projects
Ten to twelve weeks. Architecture, trade-offs, failure modes, deployment, and evidence—the project that carries an interview.
LoRA fine-tuning of an open-weight model on a specialist corpus, benchmarked against the base model and a RAG baseline.
You walk away with
Temporal models over video for activity or anomaly detection, with an alerting path for the flagged frames.
You walk away with
Explore more
Bring us a product brief, a business problem, or a final-year project. We’ll turn it into a clear scope, a working build, and a handover you fully own.
Prefer email? info@tenzok.in