Locomotion & Controls Engineer

Innefu; Delhi; On-site; INR 1,800,000 - 3,800,000; Full time

Job summary

Innefu Labs is seeking a robotics research engineer to design and train gait controllers for legged robots, bridging simulation and real-world testing. You will build simulation environments, create diverse gaits, and transfer controllers to hardware, validating performance on real robots.

The role requires hands-on experience with C++/Python, state estimation, and multiple physics engines. A strong research background in legged robotics and published work is valued.

Qualifications

• Strong background in legged locomotion and gait control.
• Experience transferring controllers from simulation to real robots.
• Proficiency with C++ and Python; state estimation from sensors.
• Experience with at least one physics simulator (Isaac Sim / MuJoCo / PyBullet / Gazebo / RaiSim).

Responsibilities

• Build the simulation environment with randomized rough terrain.
• Develop gaits (walk, trot, stairs, crawl) using RL, MPC, or both.
• Transfer controllers from simulation to real robot and tune them in field tests.
• Write state estimation (body pose and velocity) from IMU and joint sensors.
• Specify actuator and leg requirements to choose the off-the-shelf supplier.

Skills

C++

Python

State estimation

MPC

Reinforcement learning

Education

MTech/PhD in legged locomotion

BTech/MTech/PhD in Mechanical, Electrical, Aerospace, Robotics or Control Systems

Tools

Isaac Sim

MuJoCo

PyBullet

Gazebo

RaiSim

Job description

Founded in 2010, Innefu Labs is anAI-driven R&D organisation focused on advanced Data Analytics andInformation Security solutions. With a strong emphasis on innovation andproduct engineering, the company develops globally competitive solutions addressingcomplex challenges in national security, cyber intelligence, and dataanalytics.

With 100+ successful deployments across theIndian Subcontinent, the Middle East, and Southeast Asia, Innefu hasestablished a strong presence in AI for National and Cyber Security. Itsproprietary products serve Defence and Intelligence agencies, Law Enforcementorganisations, Financial Intelligence Units, BFSI institutions, and Fortune 500companies.

Innefu specialises in building secure,high-performance products for sensitive and mission-critical environments, witha strong focus on innovation, reliability, scalability, and customersatisfaction

RoleOverview

Makes the robot walk, climb and recoveron mud, rock, snow and stairs — designing and training the gait controller insimulation and transferring it to the real robot.

Experience

3–8 years,

Education

MTech/PhDwith a thesis on legged locomotion. BTech/MTech/PhD in Mechanical, Electrical,Aerospace, Robotics or Control Systems. Very few people in India have builtlegged robots, so a strong humanoid, exoskeleton or legged-research backgroundalso counts.

Responsibilities

• Build the simulationenvironment with randomised rough terrain.
• Develop gaits (walk, trot,stairs, crawl) using reinforcement learning, model predictive control (MPC), orboth.
• Transfer controllers fromsimulation to the real robot (sim-to-real) and tune them in field tests.
• Write state estimation (bodypose and velocity) from IMU and joint sensors.
• Specify actuator and legrequirements to choose the off-the-shelf supplier.

Musthave

• C++ and Python.
• Rigid-body dynamics and controltheory: MPC, whole-body control, or RL for locomotion (PPO).
• At least one physics simulator:Isaac Sim / Isaac Lab, MuJoCo, PyBullet, Gazebo or RaiSim.
• Has run a controller on realrobot hardware, not only in simulation.

Goodto have

• Hands-on with commercialquadrupeds (Unitree, ANYmal, Spot, Deep Robotics) or their SDKs.
• Open-source legged stacks:legged_gym, OCS2, Pinocchio, Drake, Crocoddyl.
• Publications at ICRA, IROS,CoRL, RSS or Humanoids.
• Kalman filters / stateestimation; terrain-aware foothold planning.

Requirements

Responsibilities

• Build the simulationenvironment with randomised rough terrain.
• Develop gaits (walk, trot,stairs, crawl) using reinforcement learning, model predictive control (MPC), orboth.
• Transfer controllers fromsimulation to the real robot (sim-to-real) and tune them in field tests.
• Write state estimation (bodypose and velocity) from IMU and joint sensors.
• Specify actuator and legrequirements to choose the off-the-shelf supplier.

Musthave

• C++ and Python.
• Rigid-body dynamics and controltheory: MPC, whole-body control, or RL for locomotion (PPO).
• At least one physics simulator:Isaac Sim / Isaac Lab, MuJoCo, PyBullet, Gazebo or RaiSim.
• Has run a controller on realrobot hardware, not only in simulation.

Goodto have

• Hands-on with commercialquadrupeds (Unitree, ANYmal, Spot, Deep Robotics) or their SDKs.
• Open-source legged stacks:legged_gym, OCS2, Pinocchio, Drake, Crocoddyl.
• Publications at ICRA, IROS,CoRL, RSS or Humanoids.
• Kalman filters / stateestimation; terrain-aware foothold planning.