Senior Machine Learning Engineer

True Anomaly•Long Beach, CA

3h•$155,000 - $260,000•Onsite

About The Position

As a member of the Applied Algorithms and Autonomy team, you will design, build, and deploy core machine learning and AI capabilities for True Anomaly. You will work with a talented cross-functional team to advance technology at the intersection of artificial intelligence, machine learning, and data-driven decision-making. This will involve hands-on development across areas including object classification and discrimination, anomaly detection, and threat assessment. You are a first-principles engineer who takes ownership of the systems you build and delivers results.

Requirements

Bachelor's degree in computer science, machine learning, data science, electrical engineering, or a similar discipline
Proficient in Python
Solid understanding of statistics, probability, and optimization
Experience with ML frameworks such as PyTorch, TensorFlow, or JAX
4+ years of experience designing, training, and deploying ML models in real-world systems
Demonstrated ability to work in a multidisciplinary team and solve complex problems from first principles
Passion for spaceflight and advancing capabilities related to space domain awareness and space security

Nice To Haves

Master's or PhD in machine learning, computer science, data science, or a related discipline
Strong background in one of the following core ML disciplines: Anomaly & outlier detection: statistical, density-based, and deep learning approaches; Object discrimination: multi-class and fine-grained classification, metric learning, few-shot learning, evidential reasoning and Dempster-Shafer Theory (DST) for belief combination and conflict resolution under uncertain or incomplete sensor data; Unsupervised learning: clustering, dimensionality reduction, generative modeling; Sequential and temporal modeling: time-series analysis and sequential modeling
Experience deploying models to edge or resource-constrained environments with real-time processing requirements
Familiarity with space domain data such as space object catalog data, observational data, or RSO characterization
Experience with MLOps tooling: experiment tracking (MLflow, W&B), model versioning, CI/CD for ML pipelines
Background in model interpretability, uncertainty quantification, or safety-critical ML validation

Responsibilities

Design, implement, and test ML/AI models that support threat assessment, object discrimination, and decision-making in operationally relevant environments
Own the full ML development lifecycle — from data ingestion and feature engineering through model training, evaluation, and production deployment
Collaborate with cross-functional teams to translate operational requirements into robust, production-ready ML capabilities
Establish and maintain rigorous model evaluation practices to ensure reliability and performance in real-world conditions
Write clean, well-documented, and testable code in support of AI/ML capabilities