At Lyft, our mission is to improve people’s lives with the world’s best transportation. To do this, we start with our own community by creating an open, inclusive, and diverse organization.
Our key ML projects are:
Card Scan Model – Use Computer vision & ML to develop models that can verify actual physical credit cards for Lyft customers to confirm the ownership for credit cards and deter stolen card usage to prevent chargebacks.
Face Auth Model – Use Computer vision & ML to improve models that can detect human faces and accurately match against existing or new pictures and help verify identity & mitigate abuse at Lyft.
- Own the ML roadmap for the Computer Vision ML initiatives (Card scan, Face Auth)
- Improve our model's ability to read cards correctly and distinguish between real vs. fake cards.
- Extract facial features to create a unique embedding that can be compared with another embedding. Match extracted features with ground truth embedding.
- Check the liveness of the person and card in real-time i.e. ensure there is a real person, card behind the camera to defeat recapture/spoofing
- Develop the methodology, thresholds and assessment criteria to measure model performance.
- Evaluate the productionzed model performance against product & biz OKRs.
- 4+ years of programming experience in Python.
- Proficiency in frameworks like Pytorch, Tensorflow, or Keras.
- Experience with CV is desirable but not mandatory
- Strong programming skills, familiarity with software development cycles, solid understanding of software concepts – data structures and algorithms.
- Strong business sense and understanding of experimentation methodologies.
- Health insurance, life and personal accident insurance benefits
- Mental health benefits
- 28 days of paid time off in addition to 12 observed holidays
- Family building benefits
- 18 weeks of paid parental leave. Biological, adoptive, and foster parents are all eligible