Principal AI Engineer: Time-Series & Multimodal Sensors

1010 Analog Devices Inc.; San Jose (CA); On-site; USD 260,000 - 358,000; Full time

Benefits offered by this job

Bonus program

Health benefits (medical, vision, and

401k

Paid time off

Job summary

Analog Devices, Inc. seeks a Principal AI Engineer in Time-Series & Sensor Foundation Models to advance AI engineering at the intersection of sensing, data, and large-scale temporal modeling. You will unify multimodal sensor data into a coherent foundation for context-aware reasoning across time.

You will lead R&D on intelligent time-series agents for edge, extend foundation-scale modeling to automotive, health, and robotics, and publish at major ML venues while mentoring junior researchers.

Qualifications

• Ph.D. or equivalent in Electrical Engineering, Computer Science, or Applied Physics.
• Proven leadership in AI/ML research with embedded systems experience is highly desirable.
• Strong background in time-series, sensor data, and multimodal modeling.

Responsibilities

• Lead R&D on intelligent time-series agents for edge deployment.
• Advance multimodal sensor fusion and cross-modal alignment.
• Create benchmarking pipelines for cross-domain time-series models.
• Publish and present at top ML and signal-processing venues.
• Mentor researchers and influence Lorenz Labs’ foundation-model strategy.

Skills

Time-series ML

Signal processing

Foundation models

LoRA/Q-LoRA

DPO/PPO/RLAIF

Statistical testing

Python

Cross-disciplinary collaboration

Education

Ph.D. in Electrical Engineering, Computer Science, or Applied Physics

Tools

Python

PyTorch

Cloud platforms (AWS/GCP)

Job description

Analog Devices, Inc. seeks a Principal AI Engineer in Time-Series & Sensor Foundation Models to advance AI engineering at the intersection of sensing, data, and large-scale temporal modeling. You will unify multimodal sensor data into a coherent foundation for context-aware reasoning across time.

You will lead R&D on intelligent time-series agents for edge, extend foundation-scale modeling to automotive, health, and robotics, and publish at major ML venues while mentoring junior researchers.