Agentic AI Evaluation Engineer — Classified Edge Platforms

Anduril; California; Sur place; USD 253 000 - 336 000; Plein temps

Résumé du poste

Anduril Industries is seeking a Discovery engineer to build analysis and prototypes for difficult problems in autonomy, AI, and sensor fusion. You will develop evaluation pipelines, simulate agentic AI performance, and validate models on classified platforms and edge hardware to ensure reliable real‑world operation.

The role emphasizes ownership of evaluation frameworks, metrics design, and cross‑functional collaboration to advance mission-critical outcomes in defense technology.

Qualifications

• Bachelor's or Master's degree in Computer Science, Machine Learning, Software Engineering, Computer Engineering, Electrical Engineering, or related technical field.

Responsabilités

• Develop test scenarios and simulation environments to assess AI performance in classified simulations.
• Lead integration and validation of agentic AI on classified platforms and edge hardware.
• Build reusable evaluation pipelines, test harnesses, and dashboards for continuous validation.
• Define metrics and establish historic performance capture across models and systems.
• Partner with cross-functional teams to document results and contribute to model cards and reviews.
• Architect and maintain evaluation infrastructure from unit checks to full-system assessments.
• Troubleshoot and resolve issues uncovered in evaluation and deployment, ensuring reliability.

Connaissances

Python

Evaluation ownership

AI/ML evaluation

Simulation

Metrics discipline

Systems thinking

Program ownership

Detail-oriented

Security clearance

Formation

Bachelor's or Master's in CS/CE/EE

Outils

Go

C++

Scripting

Description du poste

Anduril Industries is seeking a Discovery engineer to build analysis and prototypes for difficult problems in autonomy, AI, and sensor fusion. You will develop evaluation pipelines, simulate agentic AI performance, and validate models on classified platforms and edge hardware to ensure reliable real‑world operation.

The role emphasizes ownership of evaluation frameworks, metrics design, and cross‑functional collaboration to advance mission-critical outcomes in defense technology.