Lead AI Evaluation Engineer—Edge & Classified Platforms

Anduril Industries, Inc.; Washington (District of Columbia); Hybrid; USD 253,000 - 336,000; Full time

Benefits offered by this job

Equity grants

Comprehensive health benefits

Job summary

Anduril Industries in Washington, DC is seeking a Discovery engineer to build evaluation pipelines for agentic AI and ML models, with focus on simulation environments and edge/classified platforms. You will own testing, metrics, and deployment readiness across complex systems.

The role emphasizes hands-on development, cross-functional collaboration, and delivering reliable evaluation infrastructure to support mission-critical AI capabilities.

Qualifications

• Technical Expertise: Bachelor’s or Master’s in CS/CS-related field.
• Programming Proficiency: 12+ years of production-grade coding, strong Python skills.
• Evaluation Ownership: experience owning evaluation or automated testing for ML/software.
• AI/ML Evaluation: designing evaluation methodologies, metrics, benchmarks.
• Simulation Experience: designing or using simulation environments for model testing.
• Metrics Discipline: defining and tracking performance metrics over time.
• Program Ownership: coordinating across teams, documenting results.
• Security Clearance: eligible for US security clearance.

Responsibilities

• Develop and maintain evaluation frameworks and pipelines for AI/ML models.
• Lead validation of agentic AI systems on classified platforms and edge hardware.
• Build reusable evaluation pipelines, test harnesses, and dashboards for monitoring.
• Define metrics and establish historic performance capture across releases.
• Collaborate with cross-functional teams to document test results and requirements.
• Own end-to-end evaluation infrastructure from unit checks to full-system assessments.
• Troubleshoot and debug issues uncovered in evaluation and deployment.

Skills

Python

Evaluation ownership

AI/ML evaluation

Simulation

Metrics discipline

Systems thinking

Program ownership

Security clearance

Education

CS/EE degree

Tools

Go

C++

Scripting

Job description

Anduril Industries in Washington, DC is seeking a Discovery engineer to build evaluation pipelines for agentic AI and ML models, with focus on simulation environments and edge/classified platforms. You will own testing, metrics, and deployment readiness across complex systems.

The role emphasizes hands-on development, cross-functional collaboration, and delivering reliable evaluation infrastructure to support mission-critical AI capabilities.