Software Engineer, Agent Platform
Core
Own and evolve the internal LLM agent framework, including core abstractions, runtime architecture, developer experience, integrations, and reliability.
Role type
Senior IC machine-learning engineer (LLM agent platform)
Builds
Internal LLM agent framework, tooling for structured tool calling, filesystem-using agents, memory and retrieval, planning loops, subagents, agent graphs, and human-in-the-loop workflows.
Domain
Artificial Intelligence / Large Language Models / Agent Systems
Deliverable
production ML models
Required skills
LLM agent framework design, orchestration patterns, agent evaluation paradigms, model post-training workflows, reliability engineering, observability, debugging, safety engineering, API design, distributed systems design
Preferred skills
LangChain, DeepAgents, Claude SDK, evaluation platforms, simulation environments, benchmark suites, agent test harnesses, Kubernetes, Docker, workflow orchestration, ML infrastructure
Technologies
LangChain, DeepAgents, Claude SDK, Kubernetes, Docker
Responsibilities
Support teams building LLM agents through framework capabilities, implementation guidance, architectural reviews, and best-practice patterns. Integrate supervised fine-tuning, offline reinforcement learning, online reinforcement learning, and environment-driven agent improvement workflows. Define evaluation suites covering task success, tool-call correctness, trajectory quality, robustness, regressions, and deployment readiness. Make pragmatic decisions about emerging agent architecture and evaluation techniques for high-stakes LLM applications.
Seniority
Senior, hands-on IC
