About CynLr
As a foundational technology building company in Robotics & AI, CynLr builds visual robots that can intuitively learn to pick & handle even unknown objects without requiring any prior training, just like a human baby fiddling with objects. CynLr calls this stack Object Intelligence (OI).
From fitting a screw to removing object out of its the plastic wrapper to automating the assembly of a car/gadget - every such object handling task that involves adapting on the fly is not prior trainable & thereby remains non-automatable across the industries. With OIs ability to learn on the fly, CynLr's focus is to universally automate factories and eliminate the need for complicated custom machines to manufacture products. Thereby simplifying manufacturing intoUniversal Factories, which can be programmatically repurposed to produce a wide variety of Products.
CynLr envisions the future factories to be decentralized, micro factories (not the Giga Factories) that could rather be hosted in your street-ends; opening up the possibility of Personalized Products liberating design of products from the constraints of manufacturability.
As a Robotics Engineer, you will develop physics-based simulations, optimize multi-arm robotic workflows, and integrate AI-driven control systems. This role involves designing, validating, and optimizing robotic motion, perception, and manipulation algorithms for real-world applications. You'll collaborate across hardware, software, and ML teams to enhance robotic autonomy and efficiency
Physics-Based Simulation Development
- Develop comprehensive physics-based models of robotic systems, environments, and interactions.
- Create and validate dynamic models incorporating rigid body dynamics, contact physics, and material properties, and compliance for multi-arm robotic systems.
- Build digital twins of physical robots and environments to replicate real-world scenarios
Algorithm Development & Implementation
- Design, implement, and validate control and motion planning algorithms for multi-arm robots, focusing on customer manipulation and grasping tasks.
- Optimize and integrate kinematics, dynamics, and force-based control strategies for real-time applications.
- Support implementation of learning-based algorithms for real-time perception and manipulation tasks, including simulation-based testing and validation.
Machine Learning
- Leverage ML for robotic applications (e.g., perception, decision-making).
- Implement learning-based algorithms for real-time perception and manipulation tasks.
Testing, Validation & Optimization:
- Establish simulation validation protocols to bridge virtual and real-world performance, ensuring accuracy and reliability.
- Develop automated test sequences and metrics to validate algorithms across diverse scenarios with varying parameters (e.g., lighting, sensor noise, object positions, contact properties)
- Analyse simulation results to optimize robotic systems for performance, safety, and reliability, proposing design improvements (architecture, algorithms, or technologies).
Collaboration & Cross-Functional Support
- Collaborate with control engineers to validate and tune control systems in simulation.
- Collaborate with Algo and software/hardware teams to refine algorithms, identify and address sequencing errors, corner cases, and bottlenecks.
- Provide actionable insights from simulation analyses to guide system improvements.
Documentation & Reporting
- Document simulation methodologies, assumptions, and validation results.
- Provide detailed reports on system performance, optimization opportunities, and experimental findings
Must have an Understanding of
- Advanced physics-based modelling and numerical methods.
- Robot kinematics, dynamics, and control systems theory.
- Simulation validation and verification techniques.
- Sensor modelling (cameras, force/torque, etc.).
- Experience with motion planning algorithms.Engineering & Analysis.
- System dynamics modelling and error analysis.
- Test plan development and root cause analysis.
- Solution feasibility studies and model validation methodologies.
Good to Have
- Experiences: Machine learning frameworks (e.g., PyTorch, TensorFlow), Computer Vision, and real-time control system implementation.
- NVIDIA Isaac Sim/Omniverse, CoppeliaSim, Mujoco, PyBullet, PhysX, Gazebo, or similar physics-based simulation frameworks
- Python and C++ for motion scripting and automation.CAD software integration and version control systems (Git).
