Applied LLM Systems Engineer

About this role

Anduril Industries is a defense technology company with a mission to transform U.S. and allied military capabilities with advanced technology. By bringing the expertise, technology, and business model of the 21st century’s most innovative companies to the defense industry, Anduril is changing how military systems are designed, built and sold. Anduril’s family of systems is powered by Lattice OS, an AI-powered operating system that turns thousands of data streams into a realtime, 3D command and control center. As the world enters an era of strategic competition, Anduril is committed to bringing cutting-edge autonomy, AI, computer vision, sensor fusion, and networking technology to the military in months, not years.

Team Overview

Anduril’s Technical Publications organization supports complex hardware, software, autonomy, and defense systems across multiple divisions, business lines, and programs. The Product Manager, Technical Writing Systems, owns the authoring and publishing platform. This role builds the AI systems that extend that platform so the documentation pipeline handles more work at lower cost and lower latency.

Role Specifics

As the Applied LLM Systems Engineer, your mission is to design, build, and operate production AI systems that improve how technical documentation is created, transformed, validated, maintained, and delivered. You will build and maintain AI-assisted authoring, automated publishing, and multi-agent coordination tooling for the Technical Publications pipeline. This is not a prompt-writing role. It is a systems-engineering role for someone who has already delivered production AI systems, understands evaluation and rollback, and knows how to make probabilistic systems useful in enterprise environments with structured content, strict review requirements, security boundaries, and real operational consequences. The right candidate can expand system capability while managing token usage, context efficiency, and cost at scale.

What You’ll Do

• Build production-grade LLM applications for documentation and knowledge-work workflows.

• Design orchestration for multi-step workflows that coordinate models, tools, and deterministic services safely.

• Optimize context management, token usage, caching, and workflow design for cost, latency, and task success.

• Build retrieval, structured-output, and tool-integrated systems that safely interact with enterprise content, source control, issue tracking, and documentation systems.

• Design evaluation frameworks and regression testing for prompts, models, tools, retrieval pipelines, and end-to-end workflows.

• Establish observability, auditability, rollback, and safe failure modes for AI-assisted workflows.

• Work directly with technical writers, illustrators, engineers, and documentation leadership to identify the highest-value places to apply AI and where human judgment should remain primary.

• Preserve provenance between source material, generated output, validation results, and human decisions so outputs remain reviewable, correctable, and attributable.

Required Qualifications

• 5+ years of professional software engineering experience, including building and operating production services.

• Direct experience delivering at least one production AI system with measurable adoption by its intended users.

• Experience optimizing cost, latency, and context usage in production LLM or workflow systems.

• Experience designing evaluation, observability, rollback, and failure-handling for nondeterministic systems.

• Strong proficiency in Python and modern API, data, and service-development practices, including software architecture, security boundaries, identity and access management, and data protection.

• Sound judgment about where probabilistic AI is appropriate and where deterministic software or human review is required.

• Must be eligible for Secret and higher security clearance (US).

Preferred Qualifications

• Experience designing multi-step orchestration or coordination systems across models, tools, and deterministic services.

• Experience with retrieval-augmented generation, structured outputs, tool calling, or other production LLM workflow patterns.

• Experience integrating AI capabilities into desktop or enterprise applications with limited native APIs.

• Experience in defense, aerospace, manufacturing, robotics, autonomy, aviation, or another regulated environment.

• Familiarity with technical documentation, structured authoring, content management, or comparable documentation-heavy workflows.

• Familiarity with S1000D, DITA, MIL-STD-40051, or comparable documentation frameworks.

• Experience with containerized services, cloud infrastructure, CI/CD, queues, event-driven architectures, or production monitoring.

US Salary Range $112,000 — $149,000 USD

The salary range for this role is an estimate based on a wide range of compensation factors, inclusive of base salary only. Actual salary offer may vary based on (but not limited to) work experience, education and/or training, critical skills, and/or business considerations. Highly competitive equity grants are included in the majority of full time offers; and are considered part of Anduril's total compensation package. Additionally, Anduril offers top-tier benefits for full-time employees, including:

Benefits

At Anduril, we invest in our people. Our comprehensive, competitive benefits package (available at little to no cost to employees) ensures you’re supported in health, recovery, and whatever comes next. For more information, Explore Our Benefits .

Protecting Yourself from Recruitment Scams

Anduril is committed to maintaining the integrity of our Talent acquisition process and the security of our candidates. We've observed a rise in sophisticated phishing and fraudulent schemes where individuals impersonate Anduril representatives, luring job seekers with false interviews or job offers. These scammers often attempt to extract payment or

Similar jobs

• Senior LLM Systems Engineer — Risklabs · Remote
• LLM Applications Engineer — Uncountable · New York, San Francisco, Munich or London
• AI Engineer, Multimodal LLMs — Eloquentai · San Francisco
• Software Engineer, LLM & Automation — Basis-research · New York Office
• Machine Learning Research Engineer (LLMs & AI Systems) — Tenstorrent · Boston, Massachusetts, United States; Toronto, Ontario, Canada
• Machine Learning Engineer - LLMs — Hadrian-automation · Los Angeles, CA
• Senior Staff LLM Inference Engineer — D-matrix · Remote
• Senior Systems Engineer, Legal Systems — Coreweave · Livingston, NJ / New York, NY / Sunnyvale, CA / San Francisco, CA / Bellevue, WA