Embedded AI Software Engineer

We are looking for an Embedded AI Software Engineer with a strong background in software development for resource-constrained edge hardware. In this role, you will play a crucial part in creating optimized pipelines that utilize media encoders/decoders, hardware accelerators, and AI inference runtimes on platforms such as NVIDIA Jetson, Hailo, and other edge AI SoCs. Your primary responsibility will involve designing highly efficient, low-latency modules that can operate on embedded devices, requiring deep integration with NVIDIA SDKs like Jetson Multimedia, DeepStream, and TensorRT, as well as broader GStreamer pipelines. Responsibilities include: - Implementing hardware-accelerated video processing pipelines using GStreamer, V4L2, and custom media backends. - Integrating AI inference engines utilizing NVIDIA TensorRT, DeepStream SDK, or similar frameworks such as ONNX Runtime or OpenVINO. - Profiling and optimizing model loading, preprocessing, postprocessing, and buffer management for edge runtime. You will also design software within strict memory, compute, and power constraints specific to edge hardware, leveraging multimedia capabilities and implementing fallback logic for error handling in live deployment scenarios. Additionally, collaborating with kernel modules, device drivers, and board support packages to enhance performance will be a crucial part of your role. Requirements: - Bachelor's or Master's degree in Computer Engineering, Electronics, Embedded Systems, or related fields. - 2-4 years of hands-on experience in developing for edge/embedded systems using C++. - Proficiency in C++11/14/17, multi-threaded programming, video codecs, media IO pipelines, and encoder/decoder frameworks. - Familiarity with GStreamer, V4L2, multimedia buffer handling, TensorRT, DeepStream, CUDA, and NVIDIA's multimedia APIs. - Exposure to runtimes like HailoRT, OpenVINO, or Coral Edge TPU SDK is a plus. Bonus skills include familiarity with build systems like CMake, Bazel, cross-compilation, Yocto, AI model quantization, batching, layer fusion, camera bring-up, video streaming, and live feed inference. To apply for this position, please submit your resume and portfolio details to hire@condor-ai.com with the subject line "Application: Embedded AI Software Engineer." Condor AI is an AI engineering company specializing in deploying artificial intelligence solutions in real-world scenarios. We focus on Edge AI, combining custom hardware with optimized software for fast, reliable on-device intelligence. With expertise in smart cities, industrial automation, logistics, and security, our team brings over a decade of experience in AI, embedded systems, and enterprise-grade solutions. We operate globally, aiming for lean operations and building solutions for production from system design to scaled deployment.,