What You'll Do
Design and implement hybrid architectures that combine cloud and edge-based large language models to power intelligent voice experiences in vehicles. Collaborate with LLM development teams to integrate software development kits into embedded automotive systems, ensuring smooth interoperability. Build and maintain middleware that orchestrates speech recognition, natural language understanding, and text-to-speech components for responsive, real-time interactions.
Focus on reducing end-to-end system latency while maintaining high accuracy and responsiveness. Optimize CPU and memory usage to meet strict embedded environment constraints, and improve cold-start performance for faster system readiness.
Requirements
- Minimum of three years of professional software development experience
- Strong proficiency in C++11/14 for embedded systems
- Hands-on experience with Linux or Android Automotive OS
- Familiarity with large language models, agent-based systems, retrieval-augmented generation (RAG), and associated inference frameworks
- Understanding of inter-thread and inter-process communication mechanisms
Benefits
- Join a global team focused on advancing automotive AI
- Contribute to innovations shaping the future of in-car experiences
- Work with leading automakers to redefine how vehicles understand and respond to users
- Commitment to diversity, equity, and inclusion in hiring and workplace practices
- Comprehensive security training and adherence to data privacy standards
- Respect for corporate compliance, ethical conduct, and safe work environments
- Zero tolerance for discrimination or workplace violence
