Job Title: Machie Learning Engineer
Salary: $140,000 – $170,000
Location: Washington D.C (Hybrid/Remote)
My client is an expanding start-up who are pioneering the future of space weather intelligence. Their platform leverages cutting-edge science and advanced machine learning to create fully integrated solutions which enhance resilience and mitigate risks from the space environment.
They are currently seeking a talented Machine Learning Engineer to join their team and help develop ML models that turn complex data into actionable insights, driving the next generation of space-tech applications.
Key Responsibilities:
- Design and deploy machine learning models to analyze and interpret physics-based data, especially in the areas of space weather, satellite telemetry, and atmospheric dynamics.
- Implement numerical modeling techniques to simulate physical systems, integrating these with ML approaches for enhanced predictive accuracy.
- Collaborate with cross-functional teams to understand project requirements and to translate complex, physics-based processes into ML solutions.
- Optimize model performance and scalability for deployment on cloud platforms (AWS).
- Implement data preprocessing, feature engineering, and data augmentation techniques to improve model accuracy.
- Build, maintain, and improve data pipelines, ensuring the seamless flow of data from ingestion to deployment.
- Monitor and evaluate model performance post-deployment, making updates as needed for continuous improvement.
- Ensure models adhere to security, privacy, and regulatory standards.
Qualifications:
- Proven experience in developing and deploying machine learning models using Keras, TensorFlow, PyTorch, Jax, or similar modern frameworks.
- Experience building numerical and ML models of physics-based systems with exposure to large datasets or distributed systems.
- Strong background in data science, including experience with data preprocessing, feature engineering, and model evaluation.
- Proficiency in cloud platforms (AWS) for deploying and scaling machine learning models.
- Familiarity with containerization tools like Docker for model deployment.
- Solid understanding of statistical methods, algorithms, and performance metrics used in machine learning.
- Strong problem-solving and communication skills, and the ability to work collaboratively in a fast-paced environment.
Preferred Qualifications:
- Background in physics, atmospheric science, aerospace, electrical engineering, or a related field
- Experience building Physics-Informed ML models (PINN, DeepOnet, FNO/AFNO) using frameworks such as DeepXDE or Modulus
- Knowledge of MLOps practices, including CI/CD for ML, model versioning, and automated monitoring. Experience putting ML models into production.
- Relevant certifications in cloud platforms or machine learning frameworks.
- Experience with real-time data processing (Spark, Flink, Dataflow, Kafka, Pulsar, etc.)
- Experience debugging and maintaining live production systems on Kubernetes.