Train an Object Detector for an Autonomous-Forklift Robotics Startup
Overview
What this challenge is about.
Train an Object Detector for an Autonomous-Forklift Robotics Startup. Advanced challenge in code. Writing production code that solves real engineering proble...
The Brief
What you'll do, and what you'll demonstrate.
Train a real-time pallet-and-pedestrian detector with pedestrian recall above 0.99 at the chosen operating point and on-device latency under 35 ms per frame.
This is not a coding exercise. It is the work a software engineer does between a Jira ticket and a merged PR. That distinction matters to every hiring manager who has seen candidates solve LeetCode problems and none who have shipped production code under real constraints.
When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."
Earning criteria — what you'll demonstrate
- Train modern object detectors on domain-specific data
- Select operating points under hard safety constraints
- Profile and budget on-device inference latency
- Communicate model behavior to a safety-officer audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Deep Learning for Computer Vision
Master · Computer Vision
Strong alignment
This challenge maps to Deep Learning for Computer Vision at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Object Detection
Apply object detection to solve real industry problems and demonstrate production-level capability.
- Yolo
Apply yolo to solve real industry problems and demonstrate production-level capability.
- Edge Deployment
Apply edge deployment to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Safety Evaluation
Apply safety evaluation to solve real industry problems and demonstrate production-level capability.
- Operating Point Selection
Apply operating point selection to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Computer Vision Engineer
Shipping a safety-critical detector with on-device latency budgets is exactly the work CV engineers do at robotics companies.
This challenge sharpens
- object-detection
- yolo
- edge-deployment
Machine Learning Engineer
Profiling on-device inference and selecting operating points is core MLE work on edge-AI teams.
This challenge sharpens
- edge-deployment
- operating-point-selection
- pytorch
AI Safety Researcher
Writing the safety-case appendix and documenting pedestrian failure modes is a stepping stone into AI safety research roles for safety-critical systems.
This challenge sharpens
- safety-evaluation
- operating-point-selection
- object-detection