Responsibilities
- Develop Health Algorithms: Design, build, and validate data-driven and physics-informed models to evaluate the condition, degradation, and Remaining Useful Life (RUL) of critical Joby subsystems (e.g., propulsion, batteries, actuation, and structures)
- Partner with Subject Matter Experts (SMEs): Collaborate closely with domain experts across Flight Physics, Aircraft Design, Flight Test, Reliability, and Systems Engineering to translate physical failure modes and structural loads into actionable diagnostics and prognostic algorithms
- Characterize Physical Behavior & Operational Loads: Deeply analyze aircraft physical behavior and actual operational loads by wrangling complex sensor and time-series data from flights, simulators, and subsystem test rigs. Use these insights to isolate anomalies, detect early faults, and map the long-term degradation of critical components
- Component Usage Tracking & Damage Modeling: Develop algorithmic frameworks to track component-level operating metrics, flight cycles, and life limits. Translate real-world operational loads into cumulative fatigue/damage models to monitor and inform fleet-wide asset component replacement
- Write Production-Grade Code: Turn prototypes into clean, well-tested, maintainable, and production-ready Python code. Participate in and actively raise the bar for team code reviews and engineering best practices
- Own Pipeline Architecture: Design, build, and own robust, end-to-end data pipelines and services that scale efficiently to process massive volumes of raw flight and test data
- Support Flight & Field Validation: Work alongside test engineers and technicians to validate and harden health-monitoring solutions using real-world physical tests
- Drive Tooling Innovation: Selectively evaluate and integrate advanced ML/AI methodologies (such as automated data labeling or diagnostic assistance tooling) where they genuinely accelerate Prognostics Health Monitoring (PHM) workflows and team efficiency
Requirements
- MS or PhD in Aerospace, Mechanical, Electrical Engineering, Computer Science, or a related technical field
- 3+ years of post-graduate experience (or equivalent) focused on PHM, Condition-Based Maintenance (CBM+), or the analysis of complex electro-mechanical systems
- Exceptional, production-quality Python skills (pandas, scipy, numpy, pyspark) with a strict focus on automated testing, CI/CD pipelines, and disciplined version control (Git)—not just Jupyter notebook prototyping
- Self-driven, intellectually curious, and eager to learn and adopt new technologies
- Demonstrated ability to independently own implementation architecture and project lifecycles from ingestion to deployment with minimal supervision
- Demonstrable foundations in signal processing, time-series analysis, and frequency-domain fundamentals necessary to interpret physical sensor data
- Strong background in data analysis (algorithms, data structures, and architectures), probability, statistics, signal processing and predictive modeling
- Proven experience applying regression, neural networks, and machine/deep learning specifically for anomaly detection and fault isolation in physical hardware
- Experience leveraging Apache Spark or similar big data tools to wrangle, process, and analyze massive flight and test datasets. Experience with Databricks is a strong plus
- Strong collaborative and communication skills, with a track record of effectively working alongside multidisciplinary engineering teams
Nice to Have
- Deep understanding of rotating machinery diagnostics, vibration analysis, and aerospace failure modes. Familiarity with HUMS/AHM/IVHM certification processes is a massive plus
- Hands-on experience applying Large Language Models (LLMs), agentic frameworks, or advanced prompt engineering to accelerate technical workflows, automate data labeling, or build internal engineering assistance tools
- Experience building, monitoring, and maintaining ML pipelines in a high-stakes, safety-critical professional production environment
- Strong familiarity with relational databases (SQL, PostgreSQL) and designing custom APIs to seamlessly fetch and manipulate distributed data
