Machine Learning Engineer

Liquid XR; Los Angeles (CA); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Employee stock option program

Health care benefits (gold PPO) plus d

Open PTO

Job summary

Liquid XR is seeking a Machine Learning Engineer to build robust models for multimodal time-series sensor data and to advance from research to production in real-time systems.

The role requires expertise in Python and PyTorch, experience with low-latency pipelines, and familiarity with sensor data such as IMUs. Occasional travel may be involved, with a hybrid work arrangement in Los Angeles.

Qualifications

• Strong experience with ML for time-series data.
• Experience with transfer learning and knowledge distillation.
• Proficiency in Python and PyTorch.
• Solid understanding of signal processing fundamentals including filtering, noise, and frequency domain.
• Experience with real-world, noisy datasets.
• Experience building or deploying low-latency/real-time systems.
• Exposure to embedded or edge deployment constraints.

Responsibilities

• Design and implement machine learning models for time-series and sequential data.
• Develop algorithms to extract structured signals and latent variables from noisy sensor inputs.
• Build and optimize real-time inference pipelines that respect latency and compute constraints.
• Work on multi-modal learning and sensor fusion.
• Replace or augment classical signal processing pipelines with learned models.
• Create training strategies for windowed and streaming data.
• Develop training approaches for weakly labeled or partially observed datasets.
• Design and evaluate multi-task learning setups.
• Evaluate models using statistical metrics and application-driven performance criteria.
• Collaborate with cross-functional teams to move models from research to production.
• Explore sequence model architectures including Temporal convolutional networks, RNNs/LSTMs/GRUs, and Transformer-based sequence models.

Skills

Time-series ML

Transfer learning

Knowledge distillation

Python

PyTorch

Signal processing

Low-latency systems

Sensor data (IMUs)

Kalman filters

Probabilistic models

Multi-modal learning

Multi-task learning

Embedded/edge deployment

Temporal reasoning

Causality

End-to-end ownership

Quantitative degree backgrounds

Education

BSc or MSc in quantitative fields (computer science, engineering, physics, applied math)

Tools

Python

PyTorch

Job description

Liquid XR is hiring a Machine Learning Engineer to build advanced models that uncover meaningful signals from multimodal time-series sensor data. This hybrid role in Los Angeles, CA focuses on robust real-time algorithms designed for noisy, high-frequency inputs, with an emphasis on taking models from research to production under latency and compute constraints.

What you’ll do

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

What you bring

• Strong experience with machine learning for time-series data.
• Experience with transfer learning and knowledge distillation.
• Proficiency in Python and PyTorch (or similar frameworks).
• Solid understanding of signal processing fundamentals including filtering, noise, and the frequency domain.
• Experience working with real-world, noisy datasets.
• Experience building or deploying low-latency / real-time systems.
• Experience with sensor data such as IMUs.
• Familiarity with sensor fusion methods such as Kalman filters and 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.
• Ability to reason about temporal structure, causality, and latency.
• Strong intuition for modeling tradeoffs versus deployment constraints.
• Comfort working with imperfect, real-world data.
• End-to-end ownership from modeling to validation to deployment.
• BSc or MSc in quantitative fields (examples: computer science, engineering, physics, applied math).
• Team-oriented mindset and clear communication across cross-functional teams.
• Proactive, adaptable, resilient approach; ability to manage multiple priorities.
• Detail-oriented and committed to high-quality, well-documented work.
• Ownership mindset with full accountability from concept to completion.

Benefits

• Employee stock option program.
• Health care benefits (currently, gold PPO coverage with Blue Shield) plus dental and vision, starting within 30 days of employment.
• Open PTO company policy.

Role details

• Full-time employee position, working remotely or in our Los Angeles office.
• Compensation will be commensurate with experience and competitive with the market.
• Occasional travel may be required domestically and internationally.

Technologies: Python, PyTorch, RNNs, LSTMs, GRUs, Transformer-based sequence models, Temporal convolutional networks (TCNs), Kalman filters.