NEW YORK, NYPosted a month ago

Job summary

• Job post source

  This job is directly from Raydar

• Job overview

  The Geospatial Machine Learning Engineer at Raydar develops core localization models, integrating map data and imagery to enable real-time sensor-to-insight outputs on edge devices.

• Responsibilities and impact

  The role involves owning the geospatial ML pipeline, collecting and modeling map-centric data, building deployable models for constrained hardware like drones, defining geo data best practices, and rapidly moving concepts from design to field demos.

• Experience and skills

  Candidates should have deep GIS and geospatial ML expertise, fluency with coordinate systems and map projections, experience with autonomous systems or remote sensing, and skills in deploying models to embedded/edge runtimes; knowledge of C++/Rust, drone navigation, and probabilistic filtering is a plus.

• Unique job features

  The job features challenging work on precise localization using inexpensive hardware and networks of sensors, emphasizing rapid iteration on creative solutions.

Company overview

Raydar is a versatile company with multiple branches and services across various industries. Primarily, Raydar operates as a marketing information services and research agency, providing industry benchmarking and customer satisfaction insights. Additionally, Raydar has a presence in the media sector through Raydar Media, which focuses on financing, co-production, and distribution of content. The company also runs a search engine for stock photos, offering a vast collection from global brands. With offices in locations such as Suwanee, GA, and Santa Monica, CA, Raydar continues to innovate and provide solutions to supercharge business growth.

How to land this job

• Tailor your resume to highlight your expertise in geospatial machine learning, emphasizing your experience with GIS, map projections, and satellite imagery, as these are core to Raydar's localization models.

• Emphasize your skills in building and deploying machine learning models on embedded and edge devices, showcasing familiarity with CUDA, ONNX, or TensorRT to align with Raydar’s hardware constraints.

• Apply through multiple channels including Raydar’s corporate website and LinkedIn to maximize your application’s visibility and increase your chances of being noticed.

• Connect with current employees in Raydar’s geospatial or machine learning divisions on LinkedIn. Use ice breakers like commenting on recent company projects involving drone navigation or asking about their approach to edge deployment challenges.

• Optimize your resume for ATS by incorporating keywords from the job description such as 'geospatial ML pipeline,' 'localization,' 'coordinate systems,' 'edge runtimes,' and 'satellite imagery' to ensure your resume passes automated screenings.

• Leverage Jennie Johnson’s Power Apply feature to automate applying through multiple platforms, tailor your resume for ATS, and identify LinkedIn contacts to network with, saving you valuable time and increasing your chances at Raydar.