Software Engineer – Task & Motion Planning
picklerobot · Charlestown, MA ·
- Work mode
- Hybrid
- Employment
- Full time
- Category
- Software engineering
- Experience
- 2+ years
Senior applied ML engineer at Pickle Robot owning how warehouse-unloading robots decide what and how to grasp. Day to day: designing bespoke neural architectures, running cloud training pipelines, validating grasping strategies in simulation, and deploying models to physical robots. Core stack: Python, ML systems, classical robotics, cloud (GCP preferred).
About Us
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 Software Engineer to join our Task & Motion Planning team, which decides what our robots pick, how they grasp it, and how they move safely and quickly through a cluttered, changing trailer. We're looking for someone who brings strong software engineering fundamentals, a track record of shipping production code, and a genuine interest in motion planning and grasping.
You'll design and build fast, reliable, well-tested planning systems that run on real robots every day. Your code will directly affect how many boxes come off a truck per hour and how often a robot needs a human's help, and you'll see those results on the warehouse floor.
What You'll Do
-
Design, build, and maintain production C++ and Python components of our planning stack, including motion planning, grasp selection, collision checking, and task sequencing
-
Take algorithms, your own and your teammates', from prototype to deployment, owning the architecture, performance, and robustness of the implementation
-
Profile and optimize performance-critical code so planners meet real-time cycle-time targets on robot hardware
-
Build the testing, simulation, and benchmarking infrastructure that lets the team change planning code with confidence
-
Improve the reliability of the planning stack in the field by debugging failures from production logs, building tooling for triage, and fixing root causes
-
Help raise the bar for code quality through design reviews, code reviews, and good engineering practices
What You'll Bring
-
2–4 years of experience writing and shipping production software, primarily in modern C++ (C++17 or later), with working proficiency in Python
-
Strong fundamentals in software design, data structures, algorithms, and performance optimization
-
Experience owning components end-to-end: design, implementation, testing, deployment, and ongoing support
-
Solid understanding of concurrency, memory management, and profiling tools
-
A real interest in motion planning, manipulation, and grasping, and eagerness to go deep on the algorithms alongside domain experts
-
Comfort working close to hardware and debugging problems that span software and the physical world
Nice to Have
-
Hands-on experience with motion planning or manipulation (e.g., sampling-based or optimization-based planners, trajectory generation, grasp planning)
-
Experience with CUDA or GPU performance optimization
-
Familiarity with robotics libraries and frameworks such as OMPL, Drake, FCL, or Pinocchio
-
Background in 3D geometry, kinematics, or linear algebra (Eigen or similar)
-
Experience with simulation environments and large-scale regression testing for robotics or other safety-critical systems
-
Experience deploying software on physical robots in production environments