Data Scientist

ABOUT US

E-commerce got real-time data infrastructure decades ago. Physical stores still have not. RADAR is changing that.

RADAR is building the data infrastructure layer for the physical world, starting with retail. Our hardware-enabled SaaS platform uses proprietary overhead sensors, software, and AI-powered analytics to locate every product in a store, continuously, down to the fixture.

RADAR is already deployed across 1,400+ stores with retailers including American Eagle Outfitters and Old Navy, processing tens of billions of real-world events every day, delivering 99%+ accuracy in complex, noisy environments - at fleet scale.

RADAR is one of the best-funded companies in retail technology, backed by a recent Series B financing at a $1 billion valuation. Inventory accuracy is only the beginning. We believe RADAR can become foundational infrastructure for the physical economy, powering new AI-driven commerce experiences across retail and beyond.

Join us if you want to work on a large, unsolved, technically challenging problem with an ambitious team building category-defining technology.

OUR VALUES

• Mission-Driven: We're transforming retail with cutting-edge technology and building something that truly matters.

• Collaborative Team: We thrive on curiosity, shared goals, and solving complex problems together.

• High Impact: You’ll make meaningful contributions from day one and help shape the future of our product and company.

• Clear Communication: We value honesty, humility, and respectful dialogue—everyone’s voice matters.

• Balanced Lives: We work hard, but not at the expense of well-being. We respect time, boundaries, and life outside of work.

• Diverse Perspectives: We believe better ideas come from diverse backgrounds, experiences, and viewpoints.

• Empathy-Driven Design: We build with deep respect for our end users, listening closely to their feedback and needs.

ABOUT THE JOB

We are looking for Data Scientists to help grow our research and data analysis capabilities at RADAR. The role requires extensive collaboration with teams and functions across the company ranging from product and customer success to engineering and research.

This is a hybrid role based in our Sunnyvale, CA location with a flexible hybrid work schedule of 2-3 days in the office.

Responsibilities:

• Design, build, and maintain scalable batch and real-time data pipelines powering RFID analytics

• Develop, deploy, and monitor end-to-end machine learning pipelines, including feature engineering, training, and evaluation

• Collaborate closely with research teams to improve RFID-based positioning algorithms and core modeling approaches

• Design and execute experiments and simulations from hypothesis generation through analysis and presentation of results

• Perform deep analytical investigations into datasets and systems to identify root causes and drive data-informed improvements

• Establish and evolve best practices for data science, experimentation, and research workflows

• Uphold a high standard of scientific rigor, statistical validity, and reproducibility across all work

• Partner with product managers, designers, and engineering teams to translate product requirements into data-driven solutions and features

• Build and maintain data products and dashboards that support real-time and near real-time insights

ABOUT YOU

Required:

• You have a Bachelor’s degree with equivalent practical experience or Master’s degree in a relevant field (e.g., Data Science, Computer Science, Statistics, Engineering)

• You have 2+ years of experience in a data science or applied machine learning role

• You have strong proficiency in Python and common data science libraries (NumPy, Pandas, SciPy, PyTorch etc.)

• You have strong SQL skills for data exploration, transformation and Machine Learning feature development

• You have knowledge of streaming technologies for real-time analytics and Machine Learning feature engineering

• You have solid foundation in statistics, probability, and linear algebra

• You have experience with both classical machine learning and modern deep learning techniques

• You have experience contributing to the end-to-end development lifecycle, from requirements gathering and feature development to model / pipeline implementation and deployment

• You have excellent communication and collaboration skills, with the ability to work cross-functionally

Preferred:

• You have experience with GCP data and ML stack, including BigQuery, Dataflow, Vertex AI

• You have experience orchestrating pipelines using Airflow and/or Kubeflow Pipelines

• You have experience with streaming data architectures and real-time data processing frameworks (e.g., Pub/Sub, Kafka)

• You have familiarity with stream processing frameworks such as Apache Beam or Spark Structured Streaming

• You have experience building real-time or near real-time analytics systems

• You have familiarity with BI and visualization tools such as Looker

• You have experience working with large-scale data systems and complex feature engineering pipelines

WHAT YOU'LL DO

In your first 30 days, you will:

• Onboard to our data and ML ecosystem, including Airflow, Dataflow, BigQuery, Vertex AI, and Looker

• Gain familiarity with our RFID analytics platform, data models, and existing pipelines

• Partner with team members to understand current projects, workflows, and coding standards

• Start contributing to small tasks such as debugging pipelines, improving data quality checks, or enhancing existing features

In your first 60 days, you will:

• Take ownership of well-scoped features or pipeline components, from requirements to implementation with guidance

• Contribute to feature engineering and model improvements within existing ML pipelines

• Build or enhance batch and/or real-time data pipelines

• Develop or enhance dashboards or data products in Looker

• Participate in experiment design and analysis to support improvements in system performance metrics

In your first 90 days, you will:

• Independently deliver end-to-end features, from requirements gathering through deployment into production

• Collaborate with Data Engineering in the design and implementation of scalable streaming or batch architectures

• Identify and drive improvements in data quality, pipeline reliability, or model performance

• Collaborate cross-functionally with product, design, and research to shape new data-driven features

• Begin contributing to best practices in experimentation, data science workflows, and pipeline development

At RADAR, your base pay is one part of your total compensation package. The expected base salary range for this position is $120,000 - $145,000. Individual pay is determined by work location and additional factors, including job-related skills, experience and relevant education or training.You will also be eligible to receive other benefits including: equity, comprehensive medical and dental coverage, life and disability benefits, 401k plan, flexible time off, and paid parental leave. The pay range listed for this position is a good faith and reasonable estimate of the range of possible base compensation at the time of posting.

Research has shown that women & underrepresented minorities are more likely to read lists of requirements and consider themselves unqualified if they don't meet every single one. This list represents what we're ideally looking for, but everyone has unique strengths & weaknesses, and we hire for strength & potential, not lack of weakness.

Use of artificial intelligence or a LLM such as ChatGPT during the interview process will be grounds for rejection of your application process.