Join our dynamic Local AI Automation team as a Senior System Software Engineer, where you'll be instrumental in developing and maintaining cutting-edge system-level software and infrastructure. This role is perfect for individuals passionate about deploying, benchmarking, and qualifying high-quality AI applications and models. You'll collaborate with exceptional engineers to build top-tier automation infrastructure for Local AI.

If you have a genuine enthusiasm for creating reliable and scalable automation systems within the AI ecosystem, this opportunity is an excellent fit for our collaborative environment.

Your core responsibilities will involve designing, implementing, and sustaining robust system software and infrastructure essential for running diverse AI workloads across various inference backends like Llama.cpp, Ollama, PyTorch, vLLM, WinML, and TRT-RTX.

You will define system requirements for deploying AI applications, benchmarks, and models within automation frameworks. Developing solutions to meticulously measure correctness, functionality, reliability, and overall system performance will be key.

Furthermore, you will build infrastructure for downloading AI models from multiple sources, efficiently manage a local model repository, and establish automated synchronization mechanisms to ensure the repository remains current. Analyzing extensive datasets and system workload metrics, implementing data processing infrastructure, and designing insightful visualizations will also be part of your remit.

Collaboration with internal Local AI developers is crucial for identifying and implementing system-level instrumentation, diagnostics, and debugging capabilities. This will enable rapid issue isolation and resolution. You will also design, implement, and maintain infrastructure for automated build, integration, deployment, and qualification across various inference frameworks and environments.

Understanding existing infrastructure and system software architecture, debugging issues in current frameworks, pinpointing performance bottlenecks, and devising solutions to boost system efficiency and scalability are expected.

We are seeking candidates with a minimum of 5 years of experience and a B.Tech or higher degree in Computer Science, Information Technology, Software Engineering, or a related discipline.

Exceptional analytical, systems debugging, and problem-solving skills are required, alongside the ability to effectively multitask in a fast-paced, dynamic setting.

Candidates must possess over 5 years of software development experience, with strong programming proficiency in C/C++, C#, Java, or another systems programming language. Exposure to at least one scripting language, such as Python, is also necessary.

Familiarity with system APIs, multithreaded software, process and resource management, debugging tools, or performance analysis is essential. Experience with databases, SQL, source control systems (like Git and Perforce), and CI/CD infrastructure (such as Jenkins) is highly valued.

Outstanding written and oral communication skills are a must, facilitating seamless collaboration with management and engineering teams.