Robotics Engineer – Controls, Planning & Localization

Telebortix Innovations | Noida (Delhi-NCR) | On-site | Full-time | 2–6 years

About Telebortix

Telebortix is a Noida (Delhi-NCR)-based defence-technology startup building autonomy-first unmanned systems for the Indian Armed Forces and dual-use markets. Our stack spans GNSS-denied navigation, an indigenous edge autopilot, sensor fusion, multi-agent swarm coordination and full flight and ground autonomy, fielded on tactical UAVs, heavy-lift VTOL platforms and unmanned ground vehicles.

The founding team brings more than a decade of applied autonomy research from Carnegie Mellon University and its National Robotics Engineering Center, across agricultural, aerospace and military programmes. Our systems are in active trials with the Indian Army, and we are scaling from prototype to production. The autonomy stack is the product.

The role

You will own the guidance, navigation and control (GNC) layer of our autonomy stack end to end: from algorithm design in simulation to tuned, flight-proven code on real vehicles in front of the customer. You report directly to the Founder & CEO.

What you will do

Controls

- Design, implement and tune flight and vehicle controllers (cascaded PID, LQR, MPC, geometric/nonlinear control) for multirotor, fixed-wing/VTOL and ground platforms.
- Build vehicle dynamics models and system-identification workflows; validate controllers in SITL/HITL before field deployment.
- Implement failsafe, mode-transition and degraded-sensor behaviours for safety-critical operation.

Planning
- Develop global and local motion planners (sampling-, search- and optimisation-based) for obstacle-rich, dynamic environments.
- Implement trajectory generation and tracking (minimum-snap, B-spline, MPC-based) with real-time replanning on embedded compute.
- Contribute to multi-agent planning and task allocation for swarm and air–ground teaming.

Localization
- Develop and maintain state-estimation pipelines (EKF/UKF, factor-graph smoothing) fusing IMU, barometer, magnetometer, optical flow, visual-inertial odometry,



LiDAR and radar for GNSS-denied and GNSS-degraded flight.
- Characterise drift, latency and failure modes of each sensor source and design graceful fallbacks between them.
- Work with the perception team to integrate map-based and terrain-relative localisation into the navigation stack.

Integration and field work
- Deploy and tune the stack on PX4/ArduPilot-based and in-house autopilots with ROS 2 companion computers (NVIDIA Jetson class).
- Lead flight-test campaigns: define test cards, instrument the vehicle, run tests at our UP trial site and at Army establishments, analyse logs and close the loop into code.
- Write clean, tested, documented C++/Python; take part in code review, sprint planning and design reviews.
- Support customer demonstrations and user trials, and contribute to technical proposals and reports.

What we are looking for

We weight evidence of systems that flew or drove in the real world far above coursework, papers or simulation-only work.

- B.Tech/M.Tech/MS or PhD in Robotics, Aerospace, Mechanical, Electrical Engineering, Computer Science or a related field.
- 2–6 years building autonomy for mobile robots, UAVs or UGVs, with at least one system you helped take from simulation to repeated real-world operation. Fresh PhD/MS with strong project work also considered.
- Robust foundation in control theory (linear and nonlinear control, state-space methods, stability analysis) and estimation theory (Kalman filtering, probabilistic state estimation).
- Hands-on experience with at least one of: motion planning on real hardware; state estimation / VIO / LiDAR odometry on real hardware; controller design and tuning on a flying or driving vehicle.
- Proficient in modern C++ (C++17 or later)



and Python; comfortable with real-time and resource-constrained code.
- Working knowledge of ROS 2, PX4 or ArduPilot, and Linux-based embedded compute.
- Comfortable reading flight logs, debugging sensor and timing issues in the field, and iterating quickly under test-campaign pressure.
- Clear written and spoken communication; able to explain a design trade-off to an engineer and a demonstration outcome to an Army officer.

Nice to have

- GNSS-denied or GNSS-spoofed navigation experience: VIO (VINS, OpenVINS, ORB-SLAM3), LiDAR-inertial odometry (FAST-LIO, LIO-SAM), terrain- or map-relative localisation.
- Factor-graph optimisation with GTSAM, Ceres or g2o.
- Model predictive control on embedded targets (acados, CasADi, OSQP).
- Multi-agent coordination: formation control, consensus, distributed task allocation, decentralised collision avoidance.
- Fixed-wing or VTOL transition control and L1/TECS-style guidance.
- Gazebo, Isaac Sim or AirSim for closed-loop simulation and automated regression testing.
- CUDA or GPU-accelerated pipelines on Jetson-class hardware.
- Prior work on defence, aerospace or other safety-critical programmes.
- Patents, publications or open-source contributions in GNC, SLAM or planning.

What we offer

- Ownership of a core layer of the autonomy stack in a small, senior team, with direct access to the founder and to the end user.
- Your code flying in front of the customer within weeks, not quarters; regular field trials rather than a simulation-only loop.
- Competitive salary benchmarked to the role, with ESOPs for strong performers.
- Learning budget, conference travel and support for patents and publications where programme sensitivity allows.
- Health insurance, paid leave and relocation assistance to Noida where needed.

Details

- Location: Sector 62, Noida (in office), with periodic travel to field-trial sites in Uttar Pradesh and to Army establishments across India.
- Eligibility: Indian citizens only (defence programme requirement).
- Start: Immediate; notice periods of up to 60 days accommodated.

📌 Robotics Engineer – Controls, Planning & Localization (Noida)
🏢 TelebortiX
📍 Noida