Machine Learning Engineer

Liquid XR•Los Angeles, CA

4d•Hybrid

About The Position

LiquidXR is an expanding, well-funded startup building a platform to digitize human movement. We are creating next-gen wearables using proprietary MetalGel sensor technology, capturing and feeding movement data to our machine learning-enhanced algorithms and SDKs, which connect to any modern computer or development environment. We are partnered with several high-quality companies co-developing products using our tech, and we are advancing our platform to enable all types of body movement data capture and analysis across multiple areas of use (gaming, sports, performance, XR, and more). Our tight knit hardware and software team is comprised of experts in product and UX development, biomechanics, algorithms and machine learning, software platform and experience development, electronic engineering, and soft goods industrial design. Individually and collectively, this is a team who gets things done and among us, countless products have been launched worldwide. We are passionate about creating a transformative platform and we are fortunate to work on cool products using our tech along the way. We are seeking a Machine Learning Engineer to develop advanced models for extracting meaningful signals from multimodal time-series data. This role focuses on building robust, real-time algorithms that operate on noisy, high-frequency sensor inputs. You will work on problems involving temporal modeling, representation learning, and inference under real-world constraints.

Requirements

Strong experience with machine learning for time-series data
Experience with Transfer learning and knowledge distillation techniques
Proficiency in Python and PyTorch (or similar frameworks)
Solid understanding of signal processing fundamentals (filtering, noise, frequency domain)
Experience working with real-world, noisy datasets
Experience building or deploying low-latency / real-time systems
Experience with sensor data (e.g., IMUs)
Familiarity with sensor fusion methods (e.g., Kalman filters, probabilistic models)
Experience with multi-modal or multi-task learning
Exposure to embedded or edge deployment constraints
Background in applied domains involving physical systems or human data
BSc or MSc degree in quantitative fields (e.g., computer science, engineering, physics, applied math)
Ability to reason about temporal structure, causality, and latency
Strong intuition for modeling tradeoffs vs. deployment constraints
Comfort working with imperfect, real-world data
End-to-end ownership: from modeling to validation to deployment
An Owner: You possess a powerful ownership mindset and take full accountability for your projects from concept to completion.
A Proactive Driver: You are a self-starter who can "catch the vision and run with it." You thrive with autonomy and are skilled at moving projects forward with minimal oversight.
A Team Player: You are a natural collaborator who communicates clearly and works effectively with cross-functional teams to achieve shared goals.
Adaptable and Resilient: You excel at managing multiple priorities without sacrificing quality. You see the challenges of a startup environment as opportunities.
Detail-Oriented: You have a keen eye for detail and are committed to producing high-quality, well-documented work.

Responsibilities

Design and implement machine learning models for time-series and sequential data
Develop algorithms that extract structured signals and latent variables from noisy sensor inputs
Build and optimize real-time inference pipelines with latency and compute constraints
Explore and apply architectures such as: Temporal convolutional networks (TCNs), RNNs / LSTMs / GRUs, Transformer-based sequence models
Work on multi-modal learning and sensor fusion
Replace or augment classical signal processing pipelines with learned models
Design training strategies for: Windowed and streaming data, Weakly labeled or partially observed datasets, Multi-task learning setups
Evaluate models using both statistical metrics and application-driven performance criteria
Collaborate with cross-functional teams to bring models from research to production