Senior Data Scientist

Prisma-Photonics is a rapidly growing startup company, developing the next-generation smart-infrastructure solution based on novel fiber-sensing technology (smart roads, smart cities, perimeters, and grid monitoring, etc.). The company offers an award-winning disruptive solution; a "sensor free" approach to smart infrastructure. The company is VC backed and in the revenues stage.

Combining pioneering technology in optical fiber sensing with state-of-the-art machine learning, we help prevent environmental disasters, protect human lives, and keep critical energy and transportation backbones running smoothly.

Our technology turns the optical fiber embedded along high‑voltage lines into a national‑scale sensor network. By measuring real‑time wind and thermal conditions continuously along each line segment, we transform the grid into a smart, self‑aware network whose capacity is assessed accurately and dynamically—increasing current flow through the grid so more renewable projects can connect and more electric vehicles can charge.

Conventional grid‑monitoring depends on scattered line‑mounted sensors that are highly expensive and do not scale. Our solution converts the optical fiber running inside the shield wire into a continuous, high‑resolution sensor array that observes every meter of conductor in real time. This array of acoustic sensors produces a continuous flow of high-resolution waveforms, which is enriched with topographic, asset, and weather context.

We are looking for a
Senior Data Scientist
to join our journey to reinvent how power‑grid capacity is unlocked. The ideal candidate combines deep expertise in AI, physics, and engineering, with a strong track record in handling raw sensor and time-series data. They should excel in signal processing, statistical modeling, and building production-grade analytics and data pipelines. The role demands both software engineering skill and rigorous, safety-conscious development, as it impacts critical infrastructure.

What You'll Do:

• Low‑Level Signal Processing – Transform raw millisecond‑scale waveforms into meaningful features: design signal processing pipelines, extract spectral and temporal signatures of wind‑induced motion, and craft features that power the next layers of modelling.
• Research, train, and optimize models that infer local wind speed and direction, conductor temperature and strain, and detect anomalous events—leveraging cutting‑edge AI techniques to explore a fascinating, largely untapped domain.
• Deliver physical and mathematical insights from the data; work closely with academic partners to design preprocessing, augmentation, and physics‑context layers that translate wind‑induced vibrations into accurate wind metrics.
• Write, test, and maintain reliable code that operates 24/7 in production and integrates seamlessly with utility systems.
• Shape the team's data roadmap, mentor peers, and champion best practices in MLOps, experimentation, and documentation.

What You Bring:

• Advanced degree (M.Sc. or Ph.D.) in Electrical Engineering, Physics, Applied Mathematics, Computer Science, or a related quantitative discipline.
• 5+ years of hands-on experience in developing and deploying machine learning, signal processing, or algorithmic solutions, with emphasis on raw or low-level data (e.g., sensor data, audio, video streams, or medical imaging).
• Proven expertise in time-series analysis and handling large-scale, complex datasets from acquisition to production deployment.
• Strong Python programming skills, with the ability to write clean, modular, and testable production-grade code.
• Demonstrated experience deploying ML/DSP pipelines into production environments, ideally in high-availability systems.
• Familiarity with ML/DL frameworks such as PyTorch, TensorFlow, scikit-learn, and gradient-boosting libraries (e.g., XGBoost, LightGBM).
• Strong collaboration and communication skills, with the ability to work effectively across interdisciplinary teams including software engineers, physicists, and external stakeholders.

Great to Have:

• Academic or peer-reviewed publications in machine learning, signal processing, or applied physics domains.
• Hands-on experience in physical modeling, especially systems governed by mechanical, thermal, or electromagnetic principles.
• Deep understanding of AI modeling for time-series, including sequential models, anomaly detection, and temporal forecasting.
• Strong grasp of modern deep learning architectures, optimization strategies, and regularization techniques, and experience applying deep learning to real-world signal problems, such as computer vision (CV), audio analytics, or structural health monitoring.
• Familiarity with MLOps tools and best practices, such as experiment tracking and reproducibility using platforms like TensorBoard, Weights & Biases, or ClearML.
• Prior experience in mission-critical applications (e.g., aerospace, medical, energy infrastructure) is a plus.