Software Engineer, Agent Platform
Anduril IndustriesBase Salary
$220k - $292k/yr
Responsibilities
- Own and evolve the internal LLM agent framework, including core abstractions, runtime architecture, developer experience, integrations, and reliability.
- Provide framework capabilities, implementation guidance, architectural reviews, and best-practice patterns to teams building LLM agents.
- Integrate supervised fine-tuning, offline reinforcement learning, online reinforcement learning, and environment-driven agent improvement workflows.
- Design tooling for structured tool calling, filesystem-using agents, memory and retrieval, planning loops, subagents, agent graphs, and human-in-the-loop workflows.
- Define evaluation suites measuring task success, tool-call correctness, trajectory quality, robustness, regressions, and deployment readiness.
- Track emerging agent architecture and evaluation trends and make pragmatic internal adoption decisions.
Requirements
- Strong backend engineering experience building production-quality platforms, frameworks, APIs, or infrastructure used by other engineers.
- Deep expertise designing LLM agent frameworks and evaluating orchestration patterns such as linear agents, graph-based agents, multi-agent systems, planner/executor loops, and tool-heavy agents.
- Experience designing agent evaluation methods, including trajectory evaluations, LLM-as-judge workflows, task-success metrics, tool-call correctness checks, rubric-based grading, adversarial testing, regression suites, and human review.
- Familiarity with model post-training workflows including supervised fine-tuning, preference tuning, reinforcement learning, and environment-based agent training.
- Strong judgment regarding reliability, observability, debugging, and safety for LLM applications in high-stakes settings.
- Ability to work with partner teams, clarify ambiguous product needs, and turn them into reusable platform capabilities.
- Preferred: experience with Langchain Deepagents or Claude SDK.
- Preferred: experience building evaluation platforms, simulation environments, benchmark suites, or agent test harnesses.
- Preferred: experience with Kubernetes, Docker, distributed systems, workflow orchestration, or ML infrastructure.
- Preferred: familiarity with defense, robotics, command-and-control, autonomy, or operational planning domains.
Benefits
- Full-time employees receive comprehensive competitive benefits available at little to no cost.
- The role offers a base salary range of $220,000—$292,000 USD.
- Highly competitive equity grants are included in the majority of full-time offers.
- The posting does not state a work arrangement or location schedule.
Tech Stack
Categories
About Anduril Industries
Anduril is not a traditional defense contractor. We are shaping the future of defense, transforming US & allied military capabilities with advanced technology. We emphasize speed and results and control our products from start to finish, including funding R&D to selling finished products off the shelf. Today, Anduril is in a rapid growth phase, deploying technology in diverse locations and developing path-making products that will change defense forever. We believe that everyone at Anduril can be a catalyst. Your perspective can change lives, and we want to help you make your mark. Our team includes thinkers and doers working interdependently. We bring the brightest minds and best-in-class talent together with veterans who have lived the problems of our warfighters. If you like building quickly and seeing your work deployed in the real world, we want you at Anduril. With offices in Orange County, Washington DC, Seattle, Boston, Atlanta, London, and Sydney, our reach is wide. Check out our careers page at https://www.anduril.com/careers or send us an email at careers@anduril.com.