Software Engineer, Agent Platform

What you'll do

• Own and evolve the internal LLM agent framework, including core abstractions, runtime architecture, and reliability.
• Provide framework capabilities, implementation guidance, and architectural reviews to support multiple business lines.
• Integrate model post-training workflows such as supervised fine-tuning and reinforcement learning with machine learning teams.
• Design tooling for structured tool calling, memory retrieval, planning loops, and human-in-the-loop workflows.
• Define comprehensive evaluation suites to measure task success, trajectory quality, and deployment readiness.
• Research emerging agent architecture and evaluation trends to make pragmatic internal adoption decisions.
• Translate ambiguous product needs from partner teams into reusable platform capabilities.

What we're looking for

• Strong backend engineering experience building production-quality platforms, frameworks, APIs, or infrastructure used by other engineers.
• Deep expertise in LLM agent framework design, including orchestration patterns like linear, graph-based, multi-agent, and tool-heavy agents.
• Experience designing agent evaluation paradigms, including trajectory evaluations, LLM-as-judge workflows, and adversarial scenario testing.
• Familiarity with model post-training workflows such as SFT, 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 to turn ambiguous product needs into reusable platform capabilities.
• Experience with agent frameworks like Langchain Deepagents or Claude SDK (preferred).
• Experience with Kubernetes, Docker, distributed systems, workflow orchestration, or ML infrastructure (preferred).