The Autonomous Vehicle (AV) organization needs to establish pragmatic, data-backed methodologies for measuring trust and confidence in AV behavior validation results across simulation and real-world road testing to inform AV launch and release decisions.
Requirements
- Strong background in simulation-to-road correlation, statistical modeling, and confidence estimation.
- Proficiency in Python, SQL, and data visualization tools (e.g., Jupyter, Looker, Tableau).
- Ability to simplify complex analytical methods into practical frameworks for production environments.
- Experience in autonomous vehicle development, ADAS systems, or robotics.
- Familiarity with simulation environments and large-scale data analysis.
- Proven ability to design confidence metrics and validation strategies for safety-critical systems.
- Experience building dashboards and visualization tools for decision-making.
Responsibilities
- Develop and operationalize data-driven methodologies for measuring trust and confidence in AV behavior validation results.
- Establish correlation frameworks between simulation-based and road-based validation outcomes to ensure consistency and reliability.
- Simplify complex statistical and analytical methods into production-ready frameworks for AV behavior analysis.
- Design and implement scalable analysis pipelines that support continuous release decisions and AV launch readiness.
- Collaborate with engineering, safety, and AI teams to define confidence metrics and validation protocols.
- Provide actionable insights through data visualization and reporting tools to inform decision-making for AV behavior validation.
Other
- Hybrid: This role is categorized as hybrid in office. Remote requires leadership override and approval.
- Advanced degree in Data Science, Computer Science, Engineering, or related fields.
- 4+ years of experience in data science and analytics, preferably in safety-critical or complex systems domains.
- Excellent communication skills, capable of translating technical insights into clear, actionable recommendations.
- Strong track record of cross-functional collaboration in high-stakes engineering environments.
