Founding AI/LLM Integration Engineer

Ironflow AISan Diego, CA
18h

About The Position

About Ironflow AI We are building the world’s first AI-native ERP for defense tech — a system that thinks, reasons, and acts alongside the people who build, protect, and defend our way of life. We’re not patching old ideas with a flashy new user interface. We’re starting fresh — reimagining how software supports operations at the cutting edge of the defense tech revolution. Built by veterans, engineers, and operators who’ve lived the pain of legacy systems. Ironflow combines natural language, intelligent agents, and real-world rigor to empower the frontline with clarity and speed. If you're bold, decisive, and obsessed with impact — join us. This is where curiosity meets purpose. Why This Role Matters The AI layer is the beating heart of Ironflow. As our founding AI/LLM engineer, you won’t just write prompts — you’ll define how the system thinks. You’ll architect the orchestration layer that enables streaming chat, multi-agent coordination, and backend execution across ERP workflows. Your work will determine how our software reasons, adapts, and collaborates with users — at scale, and in real time.

Requirements

  • 5+ years of experience in Python and backend development
  • Hands-on experience with LLM APIs (e.g., OpenAI, Claude) and orchestration frameworks
  • Proven ability to design systems that combine tool use, memory, and autonomous reasoning

Nice To Haves

  • Familiarity with Django, GraphQL, or backend ERP workflows
  • Bias for action and a track record of shipping prototypes that evolve into production
  • Entrepreneurial spirit — you thrive in ambiguity, build from scratch, and think in systems

Responsibilities

  • Build the LLM orchestration layer using tools like LangChain, AutoGen, or CrewAI
  • Design agentic workflows that track state, propose actions, and complete multi-step tasks
  • Create structured prompting systems with function-calling, memory, and safety constraints
  • Prototype agent behavior: retries, fallback logic, chained reasoning, reactive flows
  • Collaborate with frontend and backend teams to power chat-driven "widget conjuring" UIs
  • Evaluate and integrate emerging frameworks for performance, safety, and extensibility
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service