Software Engineer, Agent Platform
$220k - $292k • Remote • Washington, District of Columbia, United States
Posted 9h ago
Job Location
Washington, District of Columbia, United States
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
Anduril Industries is seeking a backend software engineer to own and evolve their internal LLM agent framework. This role is crucial for integrating generative AI systems into the Lattice software platform, enhancing autonomy and reducing cognitive load for users. The engineer will build the platform that enables teams across Anduril to develop, evaluate, and deploy reliable LLM agents in mission-critical environments, working at the intersection of backend infrastructure, applied AI, agent architecture, model post-training, and evaluation tooling.
Responsibilities
- Own and evolve the internal LLM agent framework, including core abstractions, runtime architecture, developer experience, integrations, and reliability.
- Support business lines building LLM agents by providing new framework capabilities, implementation guidance, architectural reviews, and best-practice patterns.
- Partner with machine learning teams to integrate model post-training workflows like supervised fine-tuning, offline RL, online RL, and environment-driven agent improvement.
- Design tooling for modern agent patterns, including structured tool calling, filesystem-using agents, memory and retrieval, planning loops, subagents, agent graphs, and human-in-the-loop workflows.
- Define comprehensive evaluation suites to measure task success, tool-call correctness, trajectory quality, robustness, regressions, and deployment readiness.
- Stay current on emerging agent architecture and evaluation trends, and make pragmatic adoption decisions.
Requirements
- Strong backend engineering experience building production-quality platforms, frameworks, APIs, or infrastructure used by other engineers.
- Deep expertise in LLM agent framework design, including tradeoffs between different orchestration patterns (linear agents, graph-based agents, multi-agent systems, planner/executor loops, tool-heavy agents).
- Experience designing agent evaluation paradigms (trajectory evaluations, LLM-as-judge workflows, task-success metrics, tool-call correctness checks, rubric-based qualitative grading, adversarial scenario testing, regression eval suites, human-in-the-loop review).
- Familiarity with model post-training workflows (SFT, preference tuning, reinforcement learning, environment-based agent training).
- Strong judgment around reliability, observability, debugging, and safety for LLM applications in high-stakes settings.
- Ability to work directly with partner teams, understand ambiguous product needs, and translate them into reusable platform capabilities.
Benefits
- Highly competitive equity grants
- Top-tier benefits package (available at little to no cost to employees)
- Comprehensive, competitive benefits package ensuring support in health, recovery, and future endeavors.