> Markdown version of [/jobs/ext/569560-embedded-software-integration-optimization-engineer](https://www.wearedevelopers.com/jobs/ext/569560-embedded-software-integration-optimization-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Embedded Software Integration & Optimization Engineer - **Company:** Amaris - **Location:** Peoria, IL, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Board Bringup, Artificial Intelligence, Computing Platforms, Computer Vision, Profiling, Nvidia CUDA, Linux on Embedded Systems, Embedded Software, Object Detection, Systems Integration, Toolchain, System-level Testing, TensorRT, Data Pipelines - **Published:** June 19, 2026 - **Apply:** https://careers.mantu.com/brands/amaris-consulting/jobs/44118 ## About the Role * 5+ years of experience in embedded software development with a focus on AI/ML inference on edge hardware * Direct, hands-on experience with NVIDIA Jetson, Orin NX, and/or Thor IGX platforms * Proficiency with TensorRT, DeepStream, CUDA, and the broader NVIDIA SDK toolchain * Demonstrated experience running and optimizing multiple concurrent applications on a single compute platform * Strong background in computer vision, including object detection, segmentation, and classification * Ability to operate effectively in fast-paced, resource-constrained programs with aggressive delivery milestones, * Experience deploying AI workloads in industrial or safety-critical environments * Familiarity with perception pipeline architecture and sensor fusion * Knowledge of embedded Linux, real-time operating constraints, and hardware bring-up * Exposure to model quantization, pruning, or other inference optimization techniques ## Description We are looking for a hands-on Embedded Software Engineer with proven experience integrating and optimizing multiple AI applications on NVIDIA edge platforms for deployment in industrial machine environments. You will work at the intersection of real-time embedded systems and AI inference - tackling technically demanding problems under strict performance and safety constraints - helping bring intelligent perception capabilities to production-grade hardware. This is a high-impact role within a collaborative engineering team where your contributions directly shape the behavior of intelligent machines in the field., * Integrate and co-optimize multiple applications running concurrently on NVIDIA Thor IGX and Orin NX platforms * Implement and tune object detection, personnel classification, and segmentation algorithms for edge deployment * Port and adapt AI/ML inference workloads to NVIDIA hardware using TensorRT, CUDA, and related toolchains * Collaborate with safety and perception teams to validate detection performance on target hardware * Support system-level testing, benchmarking, and performance profiling * Contribute to CI/CD pipelines and validation cycles for embedded AI software, At Amaris, we strive to provide our candidates with the best possible recruitment experience. We like to get to know our candidates, challenge them, and be able to give them proper feedback as quickly as possible. Here's what our recruitment process looks like: Brief Call: Our process typically begins with a brief virtual/phone conversation to get to know you! The objective? Learn about you, understand your motivations, and make sure we have the right job for you! Interviews (the average number of interviews is 3 - the number may vary depending on the level of seniority required for the position). During the interviews, you will meet people from our team: your line manager of course, but also other people related to your future role. We will talk in depth about you, your experience, and skills, but also about the position and what will be expected of you. Of course, you will also get to know Amaris: our culture, our roots, our teams, and your career opportunities! Case study: Depending on the position, we may ask you to take a test. This could be a role play, a technical assessment, a problem-solving scenario, etc. As you know, every person is different and so is every role in a company. That is why we have to adapt accordingly, and the process may differ slightly at times. However, please know that we always put ourselves in the candidate's shoes to ensure they have the best possible experience. We look forward to meeting you! ## Related Videos - [Developing an AI.SDK](https://www.wearedevelopers.com/videos/198-developing-an-ai-sdk) - [Speeding up Web Apps performance with WebAssembly and Emscripten](https://www.wearedevelopers.com/videos/1985-speeding-up-web-apps-performance-with-webassembly-and-emscripten) - [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/videos/100099-tour-de-force-open-source-llm-inference-optimization-from-simple-to-sophisticated) - [Profiling Symfony & PHP apps with Blackfire](https://www.wearedevelopers.com/videos/265-profiling-symfony-php-apps-with-blackfire) - [Trends, Challenges and Best Practices for AI at the Edge](https://www.wearedevelopers.com/videos/630-trends-challenges-and-best-practices-for-ai-at-the-edge) - [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms) ## Related Articles - [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)