Staff AI/ML Engineer, Time-Series & Sensor Reasoning Models (Lorenz Labs)
Analog Devices22 hours ago
Base Salary
$198k - $272k/yr
Responsibilities
- Lead R&D on intelligent time-series agents and foundation models for anomaly detection, reasoning, and forecasting across multimodal sensor data.
- Advance sensor fusion and cross-modal alignment across electrical, acoustic, inertial, photonic, physiological, text, and image modalities.
- Create benchmarking pipelines covering robustness, interpretability, and hardware-performance metrics for cross-domain time-series foundation models.
- Apply LoRA, Q-LoRA, adapter tuning, contrastive alignment, DPO, and RLAIF to multimodal sensor datasets and physical-reasoning tasks.
- Research time-series embeddings, compression, memory, retrieval-augmented generation, and agentic systems for edge deployment.
- Partner with hardware, signal-processing, and systems teams to co-design real-time, energy-efficient sensing architectures.
- Design statistical experiments to support sensor-data collection and model development.
- Publish research and represent ADI at ML and signal-processing venues including NeurIPS, ICLR, ICML, ICASSP, and KDD.
- Mentor junior researchers and help shape foundation-model strategy for physical systems.
Requirements
- 6+ years of experience developing AI/ML products.
- Deep expertise in time-series ML, signal processing, and foundation models, including hands-on training or fine-tuning and evaluation of models such as Chronos, TimesFM, and TimeGPT.
- Proficiency in representation learning, time-series encoding and compression, and motif discovery in high-dimensional temporal data.
- Knowledge of time-series reasoning, cross-attention, multimodal embeddings, agentic systems, memory, and RAG.
- Experience with parameter-efficient fine-tuning and reward-based optimization methods including LoRA, Q-LoRA, DPO, PPO, and RLAIF.
- Strong knowledge of statistical hypothesis testing, experimental design, and causal discovery.
- Fluency in Python, PyTorch, and large-scale training pipelines using cloud or distributed systems such as AWS or GCP.
- Ability to collaborate across ML, hardware, and embedded-systems disciplines and translate research into deployable physical-intelligence systems.
- Preferred: Ph.D. in Electrical Engineering, Computer Science, or Applied Physics.
- Preferred: leadership combining technical solutions with business needs, particularly for embedded systems.
- Preferred: patents, publications, or open-source contributions.
Benefits
- Medical, vision, and dental coverage, 401(k), paid vacation, holidays, sick time, and other benefits.
- Discretionary performance-based bonus.
- Required travel is 10% of the time; the role is a first-shift/day position.
Tech Stack
Categories
AI ResearchML Engineering
About Analog Devices
Analog Devices, Inc. designs and sells analog, mixed-signal, RF, power, sensor, and digital signal processing ICs to OEMs across industrial, automotive, communications, consumer, and healthcare markets. Founded in 1965 and headquartered in Wilmington, Massachusetts, the NASDAQ-listed company earns revenue from catalog and application-specific semiconductors and supporting software used in applications from factory automation and vehicles to data centers and medical devices.