Senior Ml Engineer, Perception

At Serve, we set on a mission to make last mile delivery cheap, fast and reliable. The key component that enables us to that is our Autonomy software.
Serve's Autonomy starts with sensing the world – Perception and Prediction. To effectively interpret the environment around the robot and predict its future state, we rely on Machine Learning a lot.
Our Perception & Prediction team is looking for self-driven Machine Learning Engineers who will develop pragmatic solutions to big open-ended problems of the real world, and will nurture those solutions from ideation and prototyping stages to production, while continuously refining and enhancing them.
What you'll be doing

• Elevate proof-of-concept models to attain reliability and maturity at production levels, followed by iterative enhancements to boost their performance.
• Collaborate cross-functionally with the rest of the Autonomy team and other functions, including Infrastructure, QA, Hardware, and Operations.
• Investigate, prototype, and validate perception algorithms encompassing object detection, tracking, scene comprehension, and multi-sensor fusion.
• Translate complex, open-ended challenges into functional production code and machine learning models, primarily for Perception and Prediction tasks.
• Architect and execute the future design of our Perception and Prediction systems, enhancing model reusability, resource efficiency, and overall efficacy.

What makes you a strong fit

• Proficiency in OpenCV, along with proficiency in at least one prominent ML framework, such as PyTorch or TensorFlow.
• 3+ of commercial C++ programming experience.
• Competence in developing edge device perception using NVIDIA software libraries like CUDA or TensorRT.
• 3+ years of experience in the Autonomous Vehicles or Robotics industry.
• Hands-on experience with training, fine-tuning, deploying, and maintaining ML models in a production environment.
• Familiarity with various sensors such as Lidar, Mono/Stereo cameras, and IMU.

Bonus points

• Proficiency in at least two of the following areas: multi-sensor feature extraction and fusion, object detection and tracking, 3D Estimation, and SLAM.
• Publications in esteemed conferences or journals like CVPR, NeurIPS, ICCV, TPAMI, TRO, and more.
• Exposure to geometric perception algorithms and methodologies.
• Background in related Robotics domains like Motion Planning, Control, and Mapping.

More About Us
Serve Robotics is the team that created the Postmates delivery robot and brought it to life in LA, completing tens of thousands of deliveries in LA’s busiest neighborhoods. Now we're an independent company growing rapidly in order to connect people with what they need via robots designed to serve people.
We are proud to be an equal employment opportunity and affirmative action employer. Qualified applicants are considered without regards to race, color, religion, national origin, age, sex, marital status, ancestry, physical or mental disability, veteran status, gender identity, or sexual orientation.
See Serve in action
Serve at TED 2020 main stage
Compensation Range: $150K - $220K