Rivian and Volkswagen Group Technologies is looking to address the challenges of electric vehicles through technology that will set the standards for software-defined vehicles around the world by developing advanced camera systems, computer vision pipelines, GenAI model deployment, and embedded systems for next-generation automotive solutions.
Requirements
- Proven experience testing and evaluating AI models for speech technologies including a deep understanding of relevant performance metrics.
- Proficiency in testing AI models on embedded systems, with a solid understanding of the constraints of hardware resources (CPU, memory, power).
- Strong programming skills in Python and hands-on experience with test automation frameworks
- Experience with CI/CD pipelines and tools (e.g., GitLab CI, Jenkins).
- Familiarity with machine learning frameworks like TensorFlow or PyTorch.
- Hands-on experience with low-level system profiling, firmware interaction, and hardware-software integration.
- Knowledge of audio processing, acoustics, and data analysis tools (e.g., NumPy, Pandas, Matplotlib).
Responsibilities
- Lead the testing and validation of cutting-edge AI products, including voice assistants and core speech models like Wake-Word Detection (WWD), Voice Activity Detection (VAD), Text-to-Speech (TTS), and Speech-to-Text (STT).
- Design and execute comprehensive test plans to evaluate model performance, focusing on key metrics such as accuracy, latency, robustness, and computational efficiency (MIPS, memory footprint).
- Validate model behavior across a wide range of real-world acoustic conditions, including noisy environments, various accents, and far-field audio.
- Validate the deployment and integration of speech models onto embedded hardware platforms.
- Develop and execute Hardware-in-the-Loop (HIL) and Software-in-the-Loop (SIL) test strategies to simulate complex automotive environments and user interactions.
- Write and maintain robust, scalable test automation scripts and frameworks using Python to support unit, functional, stress, and end-to-end testing within a CI/CD pipeline.
- Execute long-duration and stress tests to identify regressions, performance degradation, and model drift over time, ensuring the long-term stability of our AI products.
Other
- 5+ years of experience in software quality assurance, with a strong focus on AI/ML product testing, particularly voice assistants or speech recognition systems.
- Strong analytical and problem-solving skills with a proactive approach to identifying and resolving complex system-level issues.
- Ability to interpret product requirements and OEM specifications to create comprehensive test plans and validation strategies for AI features.
- Excellent communication skills, with the ability to collaborate effectively with cross-functional technical teams.
- Familiarity with agile development methodologies and working in a dynamic, fast-paced environment.
