Staff AI Engineer

OrbitronAI

We re not building yet another AI tool we re building agentic systems that think, decide, and act autonomously inside real enterprises. This isn t just about chatbots or wrappers around LLM APIs. It s about unlocking the next paradigm of software where AI agents become teammates navigating data, taking action, coordinating with systems, and adapting over time.

As an early AI engineer, you won t just fine-tune prompts you ll architect intelligent systems that operate across CRMs, databases, compliance tools, customer workflows, and more. This is your chance to shape how agents are built and deployed in the real world, not just demoed in labs. We re looking for ambitious minds who want to build something foundational not just follow trends.

Bonus: You ll work in an environment where using AI tools to boost your own efficiency is expected, not optional.

What You ll Do

• Design and deploy cutting-edge AI agents using our orchestration layer built on n8n, Temporal, and next-gen agentic stacks.
• Build intelligent, context-aware workflows that plug directly into enterprise systems transforming how business make decisions, serve customers, and manage operations.
• Prototype fast. Iterate faster. You ll test, fail, learn, and ship production-grade AI agent flows that power real business outcomes.
• Collaborate with product and design to identify high-impact user journeys where AI can be a 10x unlock and then build them.
• Push the limits of RAG, embeddings, and vector search to bring real-time, grounded intelligence into every agent decision.
• Engineer smart integrations with OpenAI, Anthropic, Claude, and other LLMs blending in enterprise APIs, CRMs, internal tools, and more.
• Lead development of multi-agent orchestration flows: planner-executor models, memory layers, persona-based behaviors, and tool-using agents.
• Own the AI pipeline end-to-end: prompt engineering, dynamic context handling, agent simulation and evaluation, all the way to deployment and monitoring.
• Help set the bar for reliability, latency, and safety of AI outputs your work will shape how users trust AI inside their organizations.
• Work alongside curious, driven people who care deeply about shipping transformative products, not just academic demos.