An early-stage startup | Sensor-based video audio analysis | Jetson edge devices, is looking for a hands-on Machine Learning software engineer to join our technical team and drive the development of intelligent video and audio analytics modules. You will work closely with edge computing devices (Jetson), implement and optimize ML models, and integrate with Real-Time messaging systems like RabbitMQ, Kafka, and ZeroMQ.
Develop and deploy ML/ DL models for video and audio analysis on edge devices (Jetson Nano/Xavier).
Preprocess and analyze large volumes of sensor data (video/audio).
Work with Real-Time messaging and streaming systems (RabbitMQ, Kafka, ZeroMQ).
Optimize inference performance on Embedded hardware (using TensorRT, ONNX, CUDA).
Collaborate with DevOps and backend engineers to integrate models into production pipelines.
Requirements: 3+ years of hands-on experience in ML/AI for computer vision and/or audio processing.
Strong Python and/or C ++ skills; experience with PyTorch or TensorFlow.
Experience deploying models on NVIDIA Jetson or similar edge platforms.
Familiarity with messaging systems: RabbitMQ, Kafka, ZeroMQ.
Understanding of multimedia processing (OpenCV, ffmpeg, etc.).
Advantage: Experience with GStreamer, ROS, or sensor fusion systems.
Nice to Have:
Knowledge of Embedded systems and resource-constrained environments.
Experience with Real-Time video analytics or audio event detection.
Background in DSP or signal processing.
This position is open to all candidates.