Research Engineer - ADAS (ID 1281)

· Own C++ software modules for on device video capture, preprocessing, inference, and post processing on Linux.

• Implement classical image processing pipelines (denoise, resize, color space, undistortion) and CV algorithms (keypoints, homography, optical flow, tracking).
• Build and optimize distance/spacing estimation from monocular/stereo camera(s) using calibration, geometry, and/or depth-estimation networks.
• Integrate ML models (PyTorch/TensorFlow → ONNX/TensorRT/NNAPI/NPU runtimes) for DMS/ADAS events: drowsiness, distraction/gaze, phone-usage, smoking, seat belt, etc.
• Hit real time targets (FPS/latency/memory) on CPU/GPU/NPU using SIMD/NEON, multithreading, zero copy buffers.
• Write clean, testable C++, CMake builds, and Git based workflows (branching, PRs, code reviews, CI).
• Instrument logging/telemetry; debug with gdb/addr2line, sanitize and profile with perf/valgrind.
• Collaborate with data/ML teams on dataset curation, labeling specs, training/evaluation, and model handoff.
• Work with product & compliance to meet on road reliability, privacy, and regulatory expectations.

Requirements

• B.Tech/B.E. in CS/EE/ECE (or equivalent practical experience).
• 2–3 years in CV/ML or video-centric software roles. Hands on in modern C++ on Linux, with strong Git and CMake.
• Solid image processing and computer-vision foundations (camera models, intrinsics/extrinsics, distortion, PnP, epipolar geometry).
• Practical experience integrating CV/ML models on device (OpenCV + ONNX Runtime/TensorRT/NCNN/MediaPipe/NNAPI).
• Experience building real time pipelines for live video (GStreamer/FFmpeg, RTSP/RTMP, ring buffers), optimizing for latency & memory.
• Competence in multithreading/concurrency, lock free queues, and producer–consumer designs.
• Comfort with debugging & profiling on Linux targets. Requisites:
• Experience with driver monitoring or ADAS features; event logic and thresholding for production alerts.
• Knowledge of monocular depth estimation, stereo matching, or structure from motion for distance estimation.
• Model training exposure (PyTorch/TensorFlow): augmentation, evaluation (precision/recall, ROC/PR), quantization/pruning, conversion to ONNX/TensorRT/NCNN.
• Hardware acceleration (GPU/VPU/NPU, Arm NEON/DSP), YOLO/RT DETR/Lightweight backbones on edge.
• Cross compiling, Yocto/Buildroot, containerized toolchains; unit tests (gtest), static analysis (clang tidy, cppcheck), sanitizers.
• Basic familiarity with MQTT/IoT, message schemas, and over the air updates. Technical Competency:
• Languages: C++, Python
• CV/ML: OpenCV, ONNX Runtime/TensorRT/NCNN/MediaPipe; PyTorch/TensorFlow (for training/eval).
• Video: GStreamer/FFmpeg, V4L2, RTSP/RTMP.
• Build/DevOps: CMake, Git, gtest, clang-tidy, sanitizers; CI/CD (GitHub/GitLab/Bitbucket).
• Debug/Perf: gdb, perf, valgrind