Sr. Perception Engineer
About The Position
Our Company MISO develops technology that elevates human lives in the commercial kitchen. We’re engineering production-ready robotic systems that tightly integrate perception, real-time decision making, and electromechanical controls to automate the most dangerous, least desirable tasks in food preparation. That means building software that understands the physical world as it actually behaves, and hardware that can execute precisely in the face of chaos. Success is measured in uptime, throughput, and trust from our customers, not demos. Our flagship platform, Flippy, is already operating in high-volume restaurant kitchens across seven states. Zippy, our Kitchen Intelligence software centralizes all operational data in our broader ecosystem, expanding the role of AI-enabled autonomy in real-world operations. Backed by industry leaders, including Ecolab (NYSE: ECL), Miso combines the stability of a proven commercial product with the technical depth and ambition of a company passionately innovating to solve foundational problems in robotics and restaurant operations. If you’re excited by hard constraints, real customers, and the challenge of making software and machines perform reliably where failure isn’t an option, you’ll find meaningful problems to work on here. The Role As a Sr. Perception Engineer, you will design, develop, and improve perception of the environment and objects for Miso Robotics Flippy automated kitchen. This includes the fusion of data from cameras, infrared, arm position, state machine context, door sensors, and other sensors. You have an aggressive start-up mindset because we are bringing years of R&D to high-quality releases at scale.
Requirements
- BS Computer Vision (or similar)
- 5+ years of relevant industry experience; many releases of production quality deployments
- Programming in Python and C++
- ROS (Robot Operating System)
- Proficiency with Linux/Docker environments, and version control systems (e.g., Git)
- Sensor fusion (camera + lidar + IMU)
- Coordinate frames & transforms (TF)
- Vision inspection pipelines
- Image processing (filtering, edge detection, morphology)
- Object detection & classification, Object tracking (Kalman, SORT, DeepSORT)
- Pose estimation (PnP, ICP, visual odometry)
- Camera calibration (intrinsic/extrinsic)
- Machine Learning, CNN, PyTorch, Data set creation, labeling, & augmentation, VertexAI and/or AWS Sagemaker
- Excellent written and verbal interpersonal skills
- Attention to detail, analytical skills, and ability to learn / adapt quickly
- Collaborative team player with a drive to take initiative and ownership
Nice To Haves
- MS or PhD in Computer Science or related field
- Experience accelerating CV applications on GPU using CUDA or NVIDIA Deepstream SDK
- Experience building MLOps pipelines for continuous training, testing, and deployment of Vision Models
- OpenCV, HALCON, Cognex VisionPro
- Experience training and integrating Vision Language Action Models on robotic applications
Responsibilities
- Architect SW for reliability, scalability, and efficiency flow of data through the system.
- Develop robust monitoring solutions to continuously track and ensure system health
- Evolve and simplify state machines + scheduler that dictate robot behaviors and workflows
- Own the vision part of installation, updates, robustness, calibration, and performance
- Drive improved quality with every sprint and new release. Facilitate automated tests.
- Evaluate new 3rd-party sensors and algorithms
- Proactively align with other teams/components and the physical system
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Number of Employees
11-50 employees
