Staff Engineer, AI Factory (R5276)

Job description

Job responsibilities

• Write, optimize, and maintain advanced Python-based data analysis pipelines and custom analyzers (such as the Shared Analysis Tool) to parse simulation runs, extract log data, and calculate mission performance metrics.
• Develop, debug, and maintain custom C++ or Python adapters and automated test orchestration wrappers around core HM Forge to satisfy program-specific validation requirements.
• Implement programmatic scenario-generation pipelines and write domain-randomization scripts to systematically test autonomy behaviors under highly varied environmental conditions.
• Analyze simulation log files, rosbags, and network captures to isolate, reproduce, and debug autonomy software defects or simulator failures.
• Leverage generative AI and agentic AI tooling to dramatically accelerate the development, refinement, and maintenance of analysis suites used to characterize performance and validate HMS solutions.
• Build reusable agentic workflows that automate the generation and evolution of analysis suites, including automated discovery and interpretation of available test data and system outputs, intelligent identification of…
• Build, test, and write Terraform or Kubernetes configuration files to prototype and deploy distributed orchestration templates on top of the Forge Server.
• Write reusable, clear step-by-step developer guides, API documentation, and workspace templates to help program engineers implement automated simulation tests.

Job requirements

• Typically requires a Bachelor's degree in Computer Science, Computer Engineering, Aerospace Engineering, Systems Engineering, or related technical discipline, or equivalent practical experience.
• Strong software development background in Python, particularly for data analysis, scripting, and automation tooling (utilizing libraries like NumPy, Pandas, or similar).
• Hands-on experience with automated test orchestration, CI/CD, simulation environments, and container-based architectures (Docker, Kubernetes).
• Solid software engineering fundamentals, including version control (Git), automated testing, and disciplined debugging practices in a Linux environment.
• Familiarity with distributed compute frameworks or container orchestration tools is highly preferred.
• Strong technical problem-solving skills, with the ability to troubleshoot complex, asynchronous software systems.
• Ability to obtain and maintain an active U.S. SECRET security clearance (U.S. citizenship required).