Senior Machine Learning Engineer Perception
Pickle Robot Company builds Physical AI-powered robotic systems for supply-chain truck and container unloading.
Funding history
About Pickle Robot Company
The company provides the Pickle Unload Robot and Dill Autonomy Engine, combining industrial robotics, machine vision, optimal control, generative AI, and targeted human input for warehouse freight handling.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will advance the perception stack by designing and training 2D and 3D vision models for grasping and scene understanding. You will deploy optimized models to NVIDIA Orin hardware, own data quality and active-learning improvements, and integrate reliable perception outputs into the robotic control stack. You will also review code, mentor junior engineers, and help shape the perception roadmap.
Requirements
- Have 5+ years of computer vision and machine learning experience, including shipping ML products for robotics, autonomous vehicles, or IoT.
- Demonstrate expert Python and PyTorch skills and working knowledge of C++ for deployment and system integration.
- Have experience with 2D vision, including YOLO, Mask R-CNN, and Transformers.
- Have experience with 3D vision, including PointNet, grasp generation, multi-view geometry, and camera calibration.
- Be proficient with inference optimization tools such as TensorRT, ONNX Runtime, or CUDA.
- Have experience curating large-scale datasets, detecting statistical bias, and automating ML pipeline quality assurance.
- Translate product requirements into engineering tasks and communicate technical trade-offs to non-expert stakeholders.
- Be familiar with Docker, AWS or GCP, S3, EC2, labeling platforms, and experiment tracking tools.
Responsibilities
- Design and train multimodal vision models that combine 2D inputs and 3D geometry for grasping and scene understanding.
- Lead end-to-end model deployment, including graph optimization, TensorRT quantization, and runtime integration for low-latency edge inference.
- Conduct code reviews, mentor junior engineers, and contribute to the perception roadmap.
- Own and improve labeled datasets and data pipelines, including data quality, bottlenecks, active learning, and edge-case resolution.
- Write high-performance Python and C++ production code to integrate perception outputs into the robotic control stack while prioritizing safety and stability.
Benefits
- Health insurance
- Dental insurance
- Vision insurance
- Unlimited vacation
- Paid federal and state holidays
- 401(k) contributions of 5% of salary
- Company-covered travel expenses