Fraud/ML Engineer at Cox Exponential in San Francisco, CA

ABOUT KLED

Kled is building the largest opt-in human data network in the world.

We are not a labeling firm. We are not a task marketplace.

We are a consumer application where people upload their real photos, videos, and documents and get paid continuously.

We then filter, standardize, and license that data to frontier AI labs and enterprises that need fresh, rights-aware training data.

Since launching our mobile app in 2026, we have:

• Reached #1 on the App Store (Finance) with 0 paid marketing

• Scaled to 200,000+ active data contributors

• Processed 1.5–3M uploads per day

• Raised $5M+ from investors behind SpaceX, Airbnb, Coinbase, xAI, OpenAI, Anthropic, Spotify, Lyft, Uber, and more

Our mission is to let anyone download the app and earn a real living wage from uploading their data.

ABOUT THE ROLE

ML Engineer - Fraud Detection & Data Quality

Every day, millions of files hit our system.

Your job is to make sure only authentic, high-signal, human data gets through.

You’ll build:

• AI-generated image & video detection

• Reverse image search & internet plagiarism rejection

• Duplicate fingerprinting (vector + perceptual hashing)

• Copyright risk detection

• EXIF / metadata tampering detection

• Fraud network & device clustering systems

• Human-in-the-loop verification pipelines

This is adversarial ML at scale, not academic benchmarks.

Example:

A user is tasked with uploading a video of themselves taking out the trash. The user uploads a video of their dog. The upload is rejected automatically. But more complex. More requirements. At scale.

WE’RE LOOKING FOR:

• 3+ years in computer vision / machine learning (PyTorch or TensorFlow)

• Production ML deployment experience

• Strong SQL / PostgreSQL skills

• Experience with vector search (FAISS, pgvector, Pinecone)

• Image processing (OpenCV, PIL)

• Comfort shipping backend systems (TypeScript/Deno or similar)

Bonus:

• Deepfake detection

• Reverse image search systems

• Copyright detection pipelines

• Trust & Safety infrastructure

CURRENT STACK

Backend

• PostgreSQL (Supabase) – 100’s of millions of media files

• S3 storage

• Deno / TypeScript edge functions

• Python detection pipelines

Frontend

• SwiftUI (migrating to Flutter)

• Internal verification tooling