Lead Agentic AI Engineer

About Us

We are on a mission to revolutionize the F&B industry. Our goal is bold and simple: to design, build, and deploy the world's first fully autonomous AI agent for restaurants. We are looking for a visionary Lead Agentic AI Engineer to build a multi-agent ecosystem that essentially runs the restaurant—seamlessly handling everything from autonomous customer ordering and kitchen orchestration to real-time inventory adjustments. We don't need you to train foundational models from scratch; we need you to masterfully orchestrate them. If you excel at commanding multiple AI agents to work together in harmony and have deep expertise in context engineering, harness engineering, and memory, we want you at the helm.

Your Day-to-Day

Agent Architecture & Orchestration

Multi-Agent Ecosystems: Design and deploy architectures where specialized AI agents (e.g., Customer Facing Agent, Kitchen Expeditor Agent, Inventory Agent) seamlessly collaborate and communicate to execute complex restaurant operations.
Agent Directing: Define the rules of engagement, conflict resolution, and delegation protocols between multiple autonomous agents.
Tool Integration: Equip agents with the ability to safely interact with real-world restaurant environments (POS systems, payment gateways, kitchen display systems, and supplier APIs).

Context, Memory & Harness Engineering

Memory Systems: Build robust state management and memory pipelines (short-term, long-term, semantic, and episodic) so agents remember VIP customers, ongoing complex orders, and shifting daily menus.
Context Engineering: Design dynamic prompt architectures and retrieval-augmented generation (RAG) pipelines to ensure agents always have the exact context they need without hallucinating or exceeding token limits.
Harness Engineering: Develop advanced evaluation harnesses and guardrails to ensure agents behave safely, reliably, and predictably in a live, fast-paced F&B environment.

Leadership & AgentOps

Strategic Vision: Define the roadmap for our autonomous restaurant agent, transitioning from assisted AI features to full autonomy.
AgentOps & Observability: Build monitoring systems to track agent performance, tool-call failure rates, memory degradation, latency, and token economics.
Team Leadership: Lead and mentor a team of software engineers to build the infrastructure that supports your agentic vision.

What You Bring to the Table

Note: Deep hands-on experience training traditional ML models (e.g., TensorFlow, PyTorch) is NOT required for this role. We are looking for an applied AI/LLM orchestrator.

Experience: 5+ years of software engineering experience, with a proven track record of building production-grade LLM applications or agentic workflows.
Agentic Frameworks: Strong familiarity with multi-agent orchestration tools and frameworks (e.g., OpenClaw, LangChain, LlamaIndex, Semantic Kernel).
Core AI Competencies: * Deep understanding of Context Engineering (advanced prompting, context window optimization, RAG).
Expertise in Memory Management (Vector databases like Pinecone, Weaviate, or Milvus, and knowledge graphs).
Strong Harness Engineering skills (building sandboxes, evaluation loops, and deterministic guardrails for probabilistic models).
Software Engineering: Proficiency in Python, Go, or TypeScript, and experience building robust API integrations to connect AI with physical/digital systems.
Bonus Points: * Experience in POS, retail tech, F&B operations, or e-commerce systems.
Familiarity with event-driven architectures (Kafka, webhooks) to trigger agent workflows.

What We Have For You

Impact: A culture where engineers are encouraged to voice product ideas and improvements.
Growth: Internal transfer opportunities and support for your transition into Go development.
Flexibility: Hybrid work arrangement & flexible hours.
Culture: A young, fun, and energetic team with a casual dress code.
Compensation: Competitive salary package and benefits.