At Lyft, our mission is to improve peoples lives with the worlds best transportation. To do this, we start with our own community by creating an open, inclusive, & diverse organization.
We care deeply about delivering the best transportation experience; this means the best experience for the passenger & the best experience for the driver. We believe this quality of service can only be achieved with a deep understanding of our world, our cities, our streets how they evolve, how they breathe. We embrace the powerful positive impact autonomous transportation will bring to our everyday lives & with our ambition, we will become a leader in the development & operation of such vehicles. Thanks to our network, with hundreds of millions of rides every year, we have the means to make autonomy a safe reality. As a member of Level 5, you will have the opportunity to develop & deploy tomorrows hardware & software solutions & thereby revolutionize transportation.
The Behavioral Evaluation team is tackling a challenging problem in building self-driving vehicles. The goal is to assess the quality of the vehicles behavior. While some parts of what makes good driving are rather obvious, some other parts are quite hard to describe & even more difficult to translate into computer language. For example, evaluating potential contacts could be a straightforward geometrical problem, but evaluating the comfort of driving can get ambiguous & subjective. Therefore, we need to employ both techniques of geometric reasoning as well as more sophisticated data-driven machine learning approaches. If you enjoy these areas, want to learn more, be creative in building, defining, & improving these evaluators, were just the place.
While the main focus of the work is on the offline evaluation of the driving behavior, by defining these metrics you get to learn a lot about the onboard stack. Equipped with this knowledge we are expected to either provide signals for the onboard engineers or collaborate with them directly to improve the performance of the motion planning itself.
- Work on defining & improving evaluation systems of the autonomous behavior
- Leverage state of the art machine learning frameworks like PyTorch to train machine-learned models for evaluation
- Define datasets suitable for evaluation & work on the automation of their creation
- Build tools & infrastructure to understand the quality & representativeness of our metrics
- Collaborate with the frontend team to build the right UI for the users to be able to consume self-explanatory measurement reports
- Collaborate with the simulation team to ensure the metrics can be evaluated without the need for collecting new driving data
- Collaborate with the motion planning team to define the right metrics, & leverage the learnings to improve the autonomous driving performance
- Ability to produce production-quality C++ & Python code
- Strong background in math, algorithms, & data structures
- Bachelor's degree or higher in Computer Science, Electrical Engineering, Robotic, Mechanical Engineering, Aerospace Engineering, Math, or related field
- Ability to work in a fast-paced environment & collaborate across teams & disciplines
- Experience with machine learning frameworks like PyTorch or TensorFlow
- (Nice to Have) Experience with data science
- (Nice to Have) Experience with mobile robotics, motion control, motion models
- Great medical, dental, & vision insurance options
- Mental health benefits
- In addition to 12 observed holidays, salaried team members have unlimited paid time off, hourly team members have 15 days paid time off
- 401(k) plan to help save for your future
- 18 weeks of paid parental leave. Biological, adoptive, & foster parents are all eligible
- Pre-tax commuter benefits
- Lyft Pink - Lyft team members get an exclusive opportunity to test new benefits of our Ridership Program
Lyft is an equal opportunity/affirmative action employer committed to an inclusive & diverse workplace. All qualified applicants will receive consideration for employment without regards to race, color, religion, sex, sexual orientation, gender identity, national origin, disability status, protected veteran status or any other basis prohibited by law. We also consider qualified applicants with criminal histories consistent with applicable federal, state & local law.