Senior Computer Vision Engineer II

ROLE SUMMARY :

Role : Senior Computer Vision Engineer II

Industry Preference : Defence Technology / Deep-Tech / Aerospace / Drones / Robotics / Autonomous Systems / AI

Education : B.E./B.Tech in Computer Science / Electronics & Communication Engineering; M.Tech in Computer Vision / AI or related field preferred

JOB DESCRIPTION :

About Big Bang Boom Solutions :

Big Bang Boom Solutions (BBBS) is a Chennai-based deep-tech defence startup focused on developing indigenous defence and security technologies.

The company operates as a defence solutions integrator and develops advanced systems across Artificial Intelligence, UAS/Drone Technology, Electronic Warfare, Material Science, Propulsion, Communication Systems and Data Security.

BBBS develops products including anti-drone defence systems, see-through armour interfaces, smart surveillance platforms and other customised defence technologies. The company has participated in and won multiple iDEX challenges sponsored by the Indian Ministry of Defence and has received government grants and contracts for indigenous defence innovation.

Role Overview :

We are seeking an experienced Senior Computer Vision Engineer II to lead the development of spatial mapping, 3D perception and visual navigation systems for autonomous drones.

The ideal candidate will possess deep expertise in computer vision algorithms, deep learning, 3D vision, autonomous navigation and real-time AI deployment on edge/GPU platforms.

Key Responsibilities :

1. Technical Leadership :

- Lead Computer Vision teams developing perception and navigation systems for autonomous drones.

- Architect scalable vision pipelines for real-time aerial applications.

- Mentor engineers and drive technical excellence across vision-based autonomy initiatives.

2. Computer Vision & Deep Learning :

- Develop object detection systems using YOLO v7/v8/v11, RetinaNet, EfficientDet and Detectron2.

- Build small-object detection models optimised for aerial imagery.

- Implement multi-object tracking using SORT, DeepSORT and ByteTrack.

- Deploy transformer-based models including DETR and Swin Transformer.

- Develop semantic segmentation systems for terrain classification and scene understanding.

3. 3D Vision & Spatial Mapping :

- Implement Visual SLAM using frameworks such as ORB-SLAM3 and RTAB-Map.

- Develop depth estimation using stereo vision and monocular depth networks such as MonoDepth and MiDaS.

- Build 3D reconstruction pipelines from aerial imagery.

- Develop point-cloud processing systems using PCL and Open3D.

4. Visual Navigation :

- Develop Visual-Inertial Odometry systems for GPS-denied navigation.

- Implement optical flow for velocity estimation and obstacle avoidance.

- Develop feature detection and matching using SIFT, ORB and SuperPoint.

- Build visual servoing capabilities for precision landing and target tracking.

5. Edge AI & GPU Optimisation :

- Optimise AI models for real-time inference of less than 50 milliseconds on NVIDIA Jetson platforms.

- Implement CUDA, TensorRT and ONNX Runtime optimisations.

- Develop model quantisation and pruning techniques for edge deployment.

- Deploy mixed-precision inference using FP16 and INT8.

6. Programming & System Integration :

- Develop production-grade systems using C++ and Python.

- Work extensively with OpenCV, PyTorch / TensorFlow and CUDA.

- Integrate vision systems with PX4 / ArduPilot using ROS / ROS2.

- Implement camera calibration and multi-camera fusion.

7. Project Management :

- Manage project timelines, technical deliverables and documentation.

- Define performance benchmarks across accuracy, latency and robustness.

- Coordinate closely with hardware teams for sensor integration.

Required Skills & Qualifications :

- 9+ years of experience in Computer Vision, Image Processing and Deep Learning.

- Strong expertise in Object Detection, Object Tracking and Semantic Segmentation.

- Strong knowledge of 3D Vision, SLAM and Camera Geometry.

- Hands-on experience with CNN architectures and Vision Transformers.

- Expertise in CUDA programming and GPU optimisation.

- Experience with TensorRT and ONNX for production deployment.

- Experience with embedded vision systems and NVIDIA Jetson platforms.

- Expert proficiency in C++ and Python.

- Strong experience with OpenCV and PyTorch / TensorFlow.

- Strong understanding of Data Structures and Algorithms.

- Experience with ROS / ROS2, Git, Docker and CI/CD.

- Proven technical leadership and team-management experience.

Drone-Specific Expertise :

- Understanding of aerial imaging challenges including altitude, motion blur and perspective variations.

- Knowledge of PX4 / ArduPilot and MAVLink protocol.

- Experience with gimbal stabilisation and camera systems.

Preferred Qualifications :

- Experience with Visual-Inertial Odometry and sensor fusion using Kalman Filters, EKF or UKF.

- Knowledge of Reinforcement Learning for vision-based control.

- Publications in CVPR, ICCV, ECCV, ICRA or IROS.

- Open-source contributions to OpenCV, ROS or related ecosystems.

- Experience with photogrammetry and 3D modelling.

- Familiarity with MLOps tools such as MLflow and TensorBoard.

- Experience with Gazebo or AirSim.

- Experience with thermal or multispectral imaging.

Skills

Computer Vision, Machine Learning, GPU, Deep Learning, Edge AI, Image Processing, System Integration, C++, Python, OpenCV, PyTorch