Associate Ai/ml Engineer – Predictive Maintenance

Boeing Boeing · Aerospace · Bangalore, India, India

Associate AI/ML Engineer focused on developing predictive maintenance solutions for aircraft systems. This role involves designing and implementing AI/ML models for diagnostics, prognostics, and Remaining Useful Life (RUL) estimation, utilizing advanced techniques and MLOps practices. The position also supports the development of future AI/ML vision for Boeing and requires experience with various ML frameworks and deployment architectures.

What you'd actually do

  1. Analyze requirements, historical operational data from aircraft fleets, design and prototype innovative solutions to meet diagnostic and prognostic requirements for aircraft sub-systems as per project definition.
  2. Apply Advanced Prognostics & Health Monitoring techniques to assess the state of health, monitor component failures for aircraft systems & subsystems.
  3. Develop and refine algorithms to estimate Remaining Useful Life (RUL) and identify early-stage degradation patterns.
  4. Implement innovative, nonstandard approaches for anomaly detection, fault isolation and health prediction using physics, probabilistic, and machine learning based approaches in high level software (Python, Matlab/Simulink, etc.)
  5. Support project leads to build and productionize ML models (anomaly detection, RUL, fault classification) with modern stacks (TensorFlow, PyTorch, scikit-learn) and MLOps practices (Docker, Kubernetes, model registries).

Skills

Required

  • Python
  • TensorFlow
  • PyTorch
  • scikit-learn
  • Docker
  • Kubernetes
  • MLOps
  • anomaly detection
  • predictive maintenance
  • remaining useful life estimation
  • fault classification

Nice to have

  • Matlab/Simulink
  • time-series DBs
  • data lakes
  • Power BI
  • Tableau
  • GoJS
  • explainable AI
  • privacy-preserving methods
  • federated learning
  • edge/cloud architectures

What the JD emphasized

  • design and prototype innovative solutions
  • anomaly detection
  • fault isolation
  • health prediction
  • productionize ML models
  • MLOps practices
  • AI testing
  • verification & validation (V&V)
  • continuous post-deployment monitoring

Other signals

  • predictive maintenance
  • remaining useful life
  • anomaly detection
  • fault classification
  • MLOps