Machine Learning Engineer

About Air Space Intelligence

ASI started with a simple vision - build the Google Maps for the skies. Our mission-critical technology now powers decision-making across major airlines, the U.S. Department of Defense, and other critical infrastructure domains. Backed by top-tier investors including Andreessen Horowitz, Spark Capital, and Renegade Partners, ASI delivers operational decision superiority—compressing days of analysis into seconds of action. ASI is leading the way and pushing the boundaries of what’s possible.

What you will do:
As part of our core engineering team, you will design and deploy production-grade systems that integrate machine learning models into scalable software pipelines. You’ll develop and ship features that leverage ML to solve real-world optimization and prediction problems, working with modern infrastructure like Kubernetes, AWS, and MLOps tooling. You’ll approach problems with a software engineer’s mindset—prioritizing robustness, maintainability, and performance at scale.

What we value:

• Proficiency in Python and experience with production ML tooling and frameworks (e.g., TensorFlow, PyTorch, scikit-learn).

• Experience using LLMs in production environments — covering prompt engineering, fine-tuning, RAG systems, and frameworks like LangChain

• Strong understanding of data structures, algorithms, and software engineering best practices.

• Familiarity with classical ML, deep learning with emphasis on transformer architectures, and MLOps concepts.

• Experience building and maintaining scalable, reliable production ML systems with robust data pipelines, including expertise with Apache Beam, MLflow, and similar production-grade tools.

• Commitment to high-quality ML engineering practices, including data versioning, experiment tracking, model governance, and automated testing pipelines.

• A bias for simplicity and clarity in solving complex problems.

• Intellectual curiosity and willingness to collaborate.

• Clear communication and collaboration across cross-functional teams.

How do we hire:

We look at the interview process not as screening test but rather as an opportunity to simulate what it would look like working together. We build the interview process around you.