Principal Time-Series AI Engineer - Edge & Sensor Foundations

Analog Devices; San Jose (CA); On-site; USD 170,000 - 210,000; Full time

Job summary

Analog Devices, a global semiconductor leader, seeks a Principal AI Engineer to advance time-series and sensor foundation models across automotive, health, industrial, and robotics domains. You will build architectures unifying multimodal data—electrical, audio, motion, photonic, and physiological signals—into context-aware time-series reasoning.

Expect cross-modal research, benchmarking, and collaboration across ML, hardware, and embedded teams.

Qualifications

• 10+ years of experience developing AI/ML products.
• Proficiency in time-series ML, signal processing, and foundation models.
• Strong representation learning and time-series encoding skills.
• Experience with multimodal embedding and cross-attention architectures.
• Knowledge of statistical hypothesis testing and experimental design.

Responsibilities

• Lead R&D on intelligent time-series agents for edge, integrating multiple modalities.
• Advance cross-modal alignment between electrical, audio, motion, and photonic data.
• Create benchmarking pipelines for cross-domain time-series models.
• Apply alignment methods such as LoRA/Q-LoRA and contrastive alignment.
• Collaborate with hardware and systems teams for real-time, energy-efficient sensing solutions.
• Publish at ML and signal-processing venues and mentor researchers.

Skills

AI/ML product dev

Time-series ML

Foundation models

Python

PyTorch

Large-scale training

Distributed systems

Statistical testing

Experimental design

Cross-modal embedding

Education

Ph.D. in Electrical Eng./CS/Applied Physics

Tools

PyTorch

AWS

GCP

LoRA/Q-LoRA

Job description

Analog Devices, a global semiconductor leader, seeks a Principal AI Engineer to advance time-series and sensor foundation models across automotive, health, industrial, and robotics domains. You will build architectures unifying multimodal data—electrical, audio, motion, photonic, and physiological signals—into context-aware time-series reasoning.

Expect cross-modal research, benchmarking, and collaboration across ML, hardware, and embedded teams.