Robotics Software Engineer - Controls
Philadelphia, PA · On-site
$90K - $140K/yr
A combination of classical control and reinforcement learning applied to robotic systems. Demonstrated ability to lead technical efforts and mentor junior engineers.
Robotics Software Engineer - Controls
Philadelphia, PA · On-site
$90K - $140K/yr
A combination of classical control and reinforcement learning applied to robotic systems. Demonstrated ability to lead technical efforts and mentor junior engineers.
Robotics Software Engineer - Controls
Philadelphia, PA · On-site
$90/hr
... reinforcement learning applied to robotic systems. • Demonstrated ability to lead technical efforts and mentor junior engineers. Salary Description $90 - $140,000
Robotics Software Engineer - Controls
Philadelphia, PA · On-site
$90/hr
... reinforcement learning applied to robotic systems. • Demonstrated ability to lead technical efforts and mentor junior engineers. Salary Description $90 - $140,000
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Quick apply
Experience applying Reinforcement Learning, Vision Language Models, or Vision-Language-Action models to robotic decision-making and task planning * Familiarity with 3D perception, point cloud ...
Postdoctoral Associate - Control/Sim/RL
$60K - $90K/yr
Experience applying reinforcement learning to control of nonlinear, multi-DoF robotic systems, particularly in locomotion or underwater contexts. * Familiarity with CAD and hardware-simulation ...
Postdoctoral Associate - Control/Sim/RL
$60K - $90K/yr
Experience applying reinforcement learning to control of nonlinear, multi-DoF robotic systems, particularly in locomotion or underwater contexts. * Familiarity with CAD and hardware-simulation ...
Postdoctoral Associate - Control/Sim/RL
Philadelphia, PA · On-site
$60K - $90K/yr
Experience applying reinforcement learning to control of nonlinear, multi-DoF robotic systems, particularly in locomotion or underwater contexts. * Familiarity with CAD and hardware-simulation ...
Postdoctoral Associate - Control/Sim/RL
Philadelphia, PA · On-site
$60K - $90K/yr
Experience applying reinforcement learning to control of nonlinear, multi-DoF robotic systems, particularly in locomotion or underwater contexts. * Familiarity with CAD and hardware-simulation ...
Reinforcement Learning Robotics information
What are some common challenges faced when implementing reinforcement learning algorithms in robotics projects?
One common challenge in this role is bridging the gap between simulation and real-world environments, as algorithms that perform well in simulation may not translate directly to physical robots due to unpredictable variables and hardware limitations. Additionally, ensuring the safety and stability of the robot during training is crucial, since trial-and-error learning can sometimes result in unintended behaviors or hardware damage. Collaboration with hardware engineers and domain experts is often necessary to fine-tune models, interpret results, and iterate on solutions. Overcoming these challenges requires patience, adaptability, and strong communication skills within a multidisciplinary team.
What are the key skills and qualifications needed to thrive as a Reinforcement Learning Robotics Engineer, and why are they important?
To thrive as a Reinforcement Learning Robotics Engineer, you need a strong background in robotics, machine learning, and programming, typically supported by a degree in computer science, engineering, or a related field. Expertise with frameworks like TensorFlow or PyTorch, experience with simulation environments (such as Gazebo or ROS), and familiarity with reinforcement learning algorithms are essential. Strong problem-solving skills, creativity, and effective communication set standout professionals apart in this rapidly evolving field. These skills enable engineers to develop intelligent robotic systems that adapt and learn efficiently, driving innovation and practical deployment in real-world environments.
What is reinforcement learning in robotics?
Reinforcement learning in robotics refers to a type of machine learning where robots learn to perform tasks through trial and error, receiving feedback from their actions in the form of rewards or penalties. This approach allows robots to autonomously develop complex behaviors by interacting with their environment, rather than relying solely on pre-programmed instructions. Reinforcement learning is especially useful for tasks that are difficult to model explicitly, such as walking, grasping, or navigation. Over time, the robot improves its performance by maximizing the cumulative reward, leading to more efficient and adaptive behaviors.
What is the difference between Reinforcement Learning Robotics vs Machine Learning Engineer?
| Aspect | Reinforcement Learning Robotics | Machine Learning Engineer |
|---|---|---|
| Required Credentials | Degree in Robotics, Computer Science, or related fields; knowledge of reinforcement learning | Degree in Computer Science, Data Science, or related fields; expertise in machine learning algorithms |
| Work Environment | Robotics labs, manufacturing, autonomous systems | Tech companies, data-driven projects, software development |
| Industry Usage | Autonomous robots, industrial automation, research | Data analysis, predictive modeling, AI applications |
Reinforcement Learning Robotics focuses on applying reinforcement learning techniques to control and optimize robotic systems, often in physical environments. Machine Learning Engineers develop algorithms for a broad range of applications, including data analysis and predictive modeling. While both roles require knowledge of machine learning, Reinforcement Learning Robotics emphasizes robotics and real-world interaction, whereas Machine Learning Engineers work across various industries with software-based solutions.
What are popular job titles related to Reinforcement Learning Robotics jobs in Philadelphia, PA? For Reinforcement Learning Robotics jobs in Philadelphia, PA, the most frequently searched job titles are:
What job categories do people searching Reinforcement Learning Robotics jobs in Philadelphia, PA look for? The top searched job categories for Reinforcement Learning Robotics jobs in Philadelphia, PA are:
What cities near Philadelphia, PA are hiring for Reinforcement Learning Robotics jobs? Cities near Philadelphia, PA with the most Reinforcement Learning Robotics job openings:
$90K - $140K/yr
Other
Re-posted 7 days ago
Job description
Description
We are partnering with Ghost Robotics and have announced the search for a Robotics Software Engineer (Controls)
Description
Ghost Robotics is a robotics company building autonomous systems that operate in complex, dynamic environments. Our perception stack enables our robots to understand, localize, and navigate the world in real time, and we place a strong emphasis on robustness, performance, and maintainable engineering.
We are seeking a Senior Controls Engineer to design, implement, and deploy cutting-edge control algorithms for dynamic legged robotic systems operating in complex real-world environments. You will work across dynamics, optimization, state estimation, and real-time software owning both algorithmic innovation and system-level performance on hardware.
This role is ideal for engineers who thrive on high-velocity problem solving, deep technical ownership, and hands-on testing and validation.
Responsibilities
Design, implement, and validate advanced control architectures (e.g., model-based, optimization-based, learning-augmented controllers) for agility and robustness.
Develop, maintain, and validate state estimation and sensor fusion pipelines (IMU, joint encoders, contact/force sensing).
Lead gait generation, footstep planning, contact scheduling, and disturbance recovery tuning.
Perform rigorous offline and real-time testing in simulation and hardware environments.
Debug and analyze system performance using logs, visualization tools, hardware experiments, and fleet data.
Build automated diagnostics, analysis scripts, and tools to improve robot reliability and field performance.
Collaborate closely with mechanical, perception, embedded, and systems teams to ensure end-to-end performance and robustness.
Write clean, maintainable, real-time-safe code in C++ and Python.
Mentor junior engineers and contribute to long-term architectural decisions.
Requirements
Requirements
Required Qualifications
Strong foundations in control theory (linear, nonlinear, optimal control) with experience in legged locomotion or other dynamic systems.
Experience with multi-body dynamics, modeling, and simulation (e.g., MuJoCo, Gazebo, Isaac Sim, PyBullet).
Hands-on experience deploying algorithms on physical robotic systems and debugging complex hardware/software interactions.
Proficiency in modern C++ (C++17/20) and Python for development and tooling.
Experience with Unix/Linux environments and software engineering best practices (version control, CI/CD).
Masters/PhD in Robotics, Mechanical, Electrical, Aerospace Engineering or equivalent work experience.
Preferred Qualifications
Experience with legged or humanoid robots and real-world locomotion challenges.
Background in whole-body control frameworks (operational space control, MPC, etc.).
Familiarity with state estimation methodologies (EKF, factor graphs, UKF).
Experience architecting data analysis pipelines and automated diagnostic systems.
Publications or significant open-source contributions in robotics, controls, or estimation.
Experience with ROS 2 and real-time middleware.
A combination of classical control and reinforcement learning applied to robotic systems.
Demonstrated ability to lead technical efforts and mentor junior engineers.