Senior Perception Software Engineer

Pickle Robot Company•Charlestown, MA

5d•Onsite

About The Position

At Pickle Robot, we're on a mission to automate global supply chains with Physical AI. Our robots work alongside warehouse teams to unload trucks and containers — one of the toughest, most understaffed jobs in logistics — making the work safer, faster, and more efficient for the people doing it. Loading trucks comes next, followed by the Dill Autonomy Engine: generalized autonomy that will eventually orchestrate robots across entire logistics processes. We're looking for a dynamic, driven Senior Perception Software Engineer to help revolutionize the future of warehouse automation. This role will focus heavily on working with 3D LiDAR and other multi-sensor arrays to tackle complex challenges in state estimation, scene perception, mapping, and localization. You will play a crucial part in writing robust, production-grade software that translates raw sensor data into actionable intelligence for our robots operating in dynamic, real-world unloading docks.

Requirements

5+ years of experience in robotics software engineering (or an MS with 3+ years of highly relevant industry experience).
Exceptional software engineering fundamentals, highly proficient in Python and C++ for production systems.
Strong mathematical foundation in linear algebra, geometry, and probabilistic robotics.
Hands-on experience building perception stacks using industry-standard tools and frameworks, including ROS/ROS2, OpenCV, Open3D, Eigen, and Git.
Hands-on experience with sensor stacks including 3D LiDARs, IMUs, and cameras.
You are a "full-stack" robotics engineer who cares about accuracy, precision, and edge cases in the physical world and can articulate architectural trade-offs to drive the best system-level decisions.

Nice To Haves

Experience with optimization libraries (Ceres Solver, GTSAM), parallel computing (CUDA), Docker, and PCL.

Responsibilities

Drive the accuracy and precision of our localization and state estimation pipelines.
Ensure reliable pose estimation of the robot's mobile base and scene components.
Develop advanced obstacle mapping for collision avoidance that thrives in messy environments.
Implement and optimize point cloud processing algorithms tailored for real-time edge compute.
Architect a robust software stack that efficiently parses and interfaces with the outputs of our machine learning models, integrating novel perception pipelines seamlessly into the core production codebase.
Improve and automate multi-sensor calibration routines.
Manage tolerance stacks and ensure high-fidelity spatial alignment across our sensor suites, guaranteeing a single source of truth for the robot.