Principal Localization Engineer – Location Intelligence

Hubble Network•San Francisco, CA

1d•$183,000 - $298,000•Hybrid

About The Position

Hubble Network is seeking a Principal Localization Engineer to lead the development of robust location computation systems leveraging Hubble's dual-stack BLE + satellite telemetry. This is a highly technical and strategic role focused on solving complex state estimation problems at scale. You'll work cross-functionally with signal processing experts, firmware engineers, and data infrastructure teams to push the limits of what's possible in dynamic, global-scale environments. This role has high visibility and direct impact on our core product performance and customer acquisition.

Requirements

7+ years of hands-on, industry experience in applied state estimation, robotics, or signal processing roles.
Deep expertise in state estimation and sensor fusion, with practical implementation of Kalman, EKF, or Particle filtering techniques.
Strong understanding of geolocation systems, signal propagation models, and statistical inference under uncertainty.
Proven track record of bringing algorithms from prototype to production in real-world, resource-constrained systems.
Strong foundational SQL skills (AWS Redshift, AWS Athena, or Trino/PrestoSQL) to pull and validate analytical datasets.
Strong Python programming skills, with emphasis on numerical methods, simulation, and performance optimization.
Experience working closely with data engineering teams or building pipelines to support analytical model development.
Strong communication skills and the ability to synthesize complex technical ideas for both technical and non-technical audiences
All applicants must be U.S. citizens or lawful permanent residents (“green card holders”) as defined by ITAR (22 CFR §120.15)

Nice To Haves

Background in robotics localization, GN&C, autonomous systems perception, or RF geolocation is a strong plus.

Responsibilities

Architect and implement cutting-edge location estimation algorithms based on BLE and satellite data, including Kalman filters, Extended Kalman Filters (EKF), and Particle Filters.
Optimize for computational efficiency, real-world performance, and cost — balancing precision with system constraints.
Build and deploy production-grade statistical and probabilistic models for state tracking and error correction.
Partner with Data Engineering to define data collection, structuring, and processing pipelines that support robust modeling.
Evaluate and iterate on models based on live system performance and simulation feedback.
Collaborate with cross-functional stakeholders, including embedded systems and backend infrastructure teams, to ensure end-to-end feasibility and integration.