Senior Backend Engineer, LLM Agent Platform

Anduril Industries, Inc.; Washington (District of Columbia); On-site; USD 220,000 - 292,000; Full time

Benefits offered by this job

Equity grants

Health benefits

Job summary

Anduril Industries in Washington, DC is seeking a backend software engineer to own and evolve our internal LLM agent framework. You will shape core abstractions, runtime architecture, and developer experiences used across engineering teams to build, evaluate, and deploy reliable LLM agents in mission-critical settings.

You will partner with ML teams on model post-training workflows and design tooling for advanced agent patterns, ensuring robust evaluation and deployment readiness.

Qualifications

• Backend engineering experience building production-quality platforms.
• Expertise in LLM agent framework design and orchestration patterns.
• Experience designing agent evaluation paradigms and rubric-based assessment.
• Familiarity with model post-training workflows (SFT, RL, etc.).
• Strong reliability, observability, and safety judgment for high-stakes deployments.
• Ability to translate ambiguous product needs into reusable platform capabilities.

Responsibilities

• Own Anduril’s internal LLM agent framework, including core abstractions and runtime architecture.
• Provide new framework capabilities and architectural guidance to multiple business lines.
• Collaborate with ML teams on model post-training workflows and evaluation.
• Design tooling for modern agent patterns: memory, retrieval, planning loops, subagents, agent graphs.
• Define comprehensive evaluation suites for task success, tool-calling accuracy, and deployment readiness.
• Stay current on agent architecture trends and advise pragmatic adoption decisions.

Skills

Backend engineering

LLM agent design

Evaluation frameworks

Post-training workflows

Reliability & safety

Team collaboration

Tools

Kubernetes

Docker

Distributed systems

Workflow orchestration

ML infrastructure

Job description

Anduril Industries in Washington, DC is seeking a backend software engineer to own and evolve our internal LLM agent framework. You will shape core abstractions, runtime architecture, and developer experiences used across engineering teams to build, evaluate, and deploy reliable LLM agents in mission-critical settings.

You will partner with ML teams on model post-training workflows and design tooling for advanced agent patterns, ensuring robust evaluation and deployment readiness.