Serve Robotics

Software Engineer, ML Performance

United States

$130,000 – $170,000Compensation
Senior (5 to 8 years), Expert & Leadership (9+ years)Experience Level
Full TimeJob Type
UnknownVisa
Robotics, AI & Machine Learning, Artificial Intelligence, Autonomous VehiclesIndustries

Requirements

Candidates should possess a Bachelor's degree in Computer Science, Robotics, Electrical Engineering, or an equivalent field, coupled with at least 3 years of experience deploying ML models on embedded or edge platforms, preferably in robotics. A minimum of 2 years of experience with CUDA, TensorRT, and other NVIDIA acceleration tools is required, along with proficiency in Python and C++ for performance-sensitive systems and experience with NVIDIA Jetson platforms and edge inference tools. Familiarity with model conversion workflows is also expected.

Responsibilities

The ML Performance Engineer will own the full lifecycle of ML model deployment on robots, from handoff to system integration, and will be responsible for converting, optimizing, and integrating trained models for Jetson platforms using NVIDIA tools. This role involves developing and optimizing CUDA kernels and pipelines for low-latency, high-throughput model inference, profiling and benchmarking ML workloads, and identifying and removing compute and memory bottlenecks. The engineer will also design and implement strategies for model quantization and compression, ensure model robustness under resource constraints, manage memory layout and concurrency for optimal GPU/CPU usage, build benchmarking pipelines, collaborate with QA and systems teams for validation, and work closely with ML researchers to influence model architectures for edge deployability.

Skills

Machine Learning
Robotics
Computer Vision
PyTorch
ONNX
TensorRT
CUDA
NVIDIA Jetson
NVIDIA tools
Nsight
nvprof
ML model deployment
Performance optimization
Edge hardware
Embedded systems

Serve Robotics

Autonomous delivery robots for food and retail

About Serve Robotics

Serve Robotics is changing the delivery industry with its self-driving robots that provide sustainable and efficient delivery solutions. Instead of using traditional vehicles, these lightweight, autonomous robots deliver small items like food and retail products, reducing carbon emissions and traffic congestion. The company operates on a delivery-as-a-service (DaaS) model, allowing businesses in the food and retail sectors to subscribe and pay based on their delivery needs. Serve Robotics aims to lead in the autonomous delivery market by offering eco-friendly solutions that enhance customer experience.

Redwood City, CaliforniaHeadquarters
2021Year Founded
$51.6MTotal Funding
POST_IPO_EQUITYCompany Stage
Food & Agriculture, Robotics & Automation, Consumer GoodsIndustries
51-200Employees

Risks

Rapid expansion may strain resources and operational capabilities.
Integration of Vebu could divert focus from core delivery services.
Over-reliance on partners like Uber and Nvidia poses potential risks.

Differentiation

Serve Robotics uses zero-emissions rovers for eco-friendly food delivery.
The company offers delivery-as-a-service with a subscription-based revenue model.
Serve Robotics integrates Vebu's Autocado for expanded automation solutions.

Upsides

Recent $80M funding supports expansion to 2,000 robots by end of 2025.
Acquisition of Vebu enhances automation offerings beyond delivery services.
Appointment of Anthony Armenta boosts AI and software capabilities.

Land your dream remote job 3x faster with AI