Senior/Staff Scientist - Algorithms & Data Products

VoltForce; San Leandro (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

VoltForce is seeking a Senior Scientist, Algorithms & Data Products to join our R&D team in the San Francisco Bay Area. You will design and implement advanced data models from multi‑modal sensor signals and own end‑to‑end modeling pipelines that translate raw data into trusted customer metrics.

The ideal candidate holds an advanced degree in a quantitative field and has 6+ years building models for real‑world sensor or process data, with strong Python and ML tooling.

Qualifications

• Advanced degree (PhD or MS with substantial experience) in a quantitative field such as physics, applied mathematics, statistics, electrical engineering, computer science, or similar, with a strong focus on data analysis and modeling.
• 6+ years of hands on experience (industry or postdoc) building models for real world sensor or process data, not just web/NLP/recommender systems.
• A track record of catching problems in data that others missed – artifacts, drift, miscalibration, or a pipeline quietly producing plausible nonsense.
• Strong Python skills and experience with scientific computing/ML tooling (NumPy, SciPy, pandas, scikit learn; familiarity with PyTorch or similar is a plus).
• Demonstrated ability to design and execute end to end analysis workflows: data ingestion and cleaning, feature engineering, model training, validation, and reporting.
• Experience with at least one of: spectroscopy, imaging, time series/multivariate process data, or other high dimensional measurement modalities.
• Solid grounding in statistics (hypothesis testing, confidence intervals, experimental design, control charts, etc.) and comfort reasoning about uncertainty and robustness.
• Experience designing or implementing automated experimental workflows or test rigs that integrate hardware and software (e.g., lab automation, instrument control, hardware in the loop setups).
• Proven ability to communicate technical results clearly, in writing and in person, to both technical and non technical stakeholders.
• Comfortable working in lab and/or industrial environments: dealing with noisy data, incomplete logging, and partially instrumented systems.

Responsibilities

• Own end to end modeling pipelines from raw sensor data to customer facing metrics and alerts.
• Develop multi modal representations of plasma‑material interactions that generalize across different materials, geometries, and processes.
• Design and implement automated experimental protocols (parameter sweeps, DOE campaigns, calibration routines) that coordinate plasma hardware, motion/robotics, sensing, and data capture.
• Work with embedded, controls, and software engineers to design deployment architectures across edge devices, host controllers, and cloud systems.
• Define performance metrics, validation strategies, and monitoring for models running in benchtop products and pilot manufacturing lines.
• Own the trustworthiness of our data – interrogate raw and derived data for instrument artifacts, drift and silent pipeline failures, and build the checks that catch a bad result before it reaches a model, a customer metric, a disclosure, or a paper.

Skills

Python programming

Data analysis

Machine learning

Statistical analysis

Modeling

End-to-end workflows

Education

PhD or MS in physics / applied mathematics / statistics / electrical engineering / CS

Tools

NumPy

SciPy

Pandas

scikit-learn

PyTorch

Job description

About The Job

Job Title: Senior Scientist, Algorithms & Data Products

Location: On-Site (San Francisco Bay Area, CA)

Job Type: Full-Time

About The Company

The company helps manufacturers make better, safer, and more reliable micro- and nano-materials. These materials are the building blocks of critical sectors of the global economy such as batteries, computer chips, aircraft components, and power systems. But, surging material demand and growing complexity are pushing production to unprecedented scales and speeds, leaving manufacturers effectively flying blind. Small, undetected variations during production lead to wastage, lower performance, higher costs, and safety risks.

The company is changing this by developing a manufacturing intelligence platform that non-destructively probes materials during production, revealing critical internal information without damaging them. Using a novel combination of cold atmospheric plasma, physics-informed machine learning, and predictive analytics, the company generates unique, real-time material fingerprints that capture material signals not accessible through conventional measurement techniques. These insights give manufacturers unprecedented visibility into how materials behave as they are made.

We turn hidden data into actionable intelligence to help manufacturers reduce variability and thus increase yield and performance. The technology can be deployed as a standalone tool or integrated directly into factory production lines. The company is currently deploying early versions of its platform with some of the largest industrial manufacturers in the world across North America, Europe, and Asia.

Role Overview

We’re looking for a Senior Scientist, Algorithms & Data Products to join our core R&D team, working at the heart of our manufacturing intelligence platform – not in a commercial analytics role. You’ll turn rich plasma sensor signals into trusted metrics and models and to build the automation that powers our next generation of experiments.

This is a high‑impact, hands‑on R&D role at the core of the company’s technology stack, shaping how we design, run, and learn from our experiments.

In This Role You Will

• Design and build algorithms that map multi‑modal sensor data (optical emission spectra, electrical signals, thermal/other sensors, process context) into robust “material fingerprints” and properties.
• Work with systems, plasma, and applications engineers to marry hardware and software: designing and automating experiment protocols for our benchtop, inline roll‑to‑roll, and robotic piece‑to‑piece platforms.
• Shape our first generation of models and metrics for battery electrodes and ceramic barrier coatings, directly influencing what customers see and trust.

What You'll Do

• Own end to end modeling pipelines from raw sensor data to customer facing metrics and alerts.
• Develop multi modal representations of plasma‑material interactions that generalize across different materials, geometries, and processes.
• Design and implement automated experimental protocols (parameter sweeps, DOE campaigns, calibration routines) that coordinate plasma hardware, motion/robotics, sensing, and data capture.
• Work with embedded, controls, and software engineers to design deployment architectures across edge devices, host controllers, and cloud systems.
• Define performance metrics, validation strategies, and monitoring for models running in benchtop products and pilot manufacturing lines.
• Own the trustworthiness of our data – interrogate raw and derived data for instrument artifacts, drift and silent pipeline failures, and build the checks that catch a bad result before it reaches a model, a customer metric, a disclosure, or a paper.

What We're Looking For

• Advanced degree (PhD or MS with substantial experience) in a quantitative field such as physics, applied mathematics, statistics, electrical engineering, computer science, or similar, with a strong focus on data analysis and modeling.
• 6+ years of hands on experience (industry or postdoc) building models for real world sensor or process data, not just web/NLP/recommender systems.
• A track record of catching problems in data that others missed – artifacts, drift, miscalibration, or a pipeline quietly producing plausible nonsense.
• Strong Python skills and experience with scientific computing/ML tooling (NumPy, SciPy, pandas, scikit learn; familiarity with PyTorch or similar is a plus).
• Demonstrated ability to design and execute end to end analysis workflows: data ingestion and cleaning, feature engineering, model training, validation, and reporting.
• Experience with at least one of: spectroscopy, imaging, time series/multivariate process data, or other high dimensional measurement modalities.
• Solid grounding in statistics (hypothesis testing, confidence intervals, experimental design, control charts, etc.) and comfort reasoning about uncertainty and robustness.
• Experience designing or implementing automated experimental workflows or test rigs that integrate hardware and software (e.g., lab automation, instrument control, hardware in the loop setups, industrial test stands).
• Proven ability to communicate technical results clearly, in writing and in person, to both technical and non technical stakeholders.
• Comfortable working in lab and/or industrial environments: dealing with noisy data, incomplete logging, and partially instrumented systems.

Nice to Have

• Comfort working with hardware APIs (e.g., vendor SDKs, REST/gRPC services, serial/fieldbus interfaces) from Python or similar, and reasoning about timing, synchronization, and error handling.
• Experience with multi‑modal data fusion (combining spectral, imaging, and process data) or related techniques in domains such as autonomous systems, medical imaging, or industrial inspection.
• Background in plasma physics, optical diagnostics, materials science, or related fields - or strong interest and ability to learn these areas quickly.
• Experience deploying models into edge or real‑time systems with latency and reliability constraints.
• Familiarity with lab automation or experiment orchestration tools (e.g., custom Python control scripts, LabVIEW, PLC/SCADA, or equivalent), and interest in building lightweight, code‑driven alternatives.
• Experience with experiment tracking, MLOps, or data‑centric tooling (e.g., MLFlow, Weights & Biases, DVC) and modern software engineering practices (Git, code reviews, CI/CD).
• Prior work with battery manufacturing, roll‑to‑roll processes, or high‑temperature coatings (e.g., turbine components) is a strong plus.