AI Engineer

HMBL • San Diego, CA

6d

About The Position

HMBL is seeking an AI Engineer passionate about building long-lived AI systems. As a Founding AI Systems Engineer, you will own the AI core of the platform, focusing on agents, tools, ontology generation, memory, retrieval, and evaluation. This role is not about model training but centers on agent architectures, semantic retrieval, knowledge representation, enterprise data systems, decision intelligence, and autonomous learning from operational data. The ideal candidate will build in an LLM-first, reasoning-first way, aiming to make the platform increasingly self-improving.

Requirements

• Deep understanding of modern AI tooling: LLM orchestration, RAG architectures, retrieval systems, and knowledge graphs in production.
• Hands-on experience with agent frameworks and orchestration tooling such as LangGraph and DSPy.
• Strong engineering fundamentals and comfort with a modern typed stack (TypeScript + Node).
• Ability to write production-quality code with a focus on reliability and scale.
• Genuine excitement for enterprise ontology induction, operational memory, decision patterns, agentic systems, and learning from operational exhaust.
• Proactive in testing assumptions and possessing deep knowledge in AI.
• Intentional about work and career, with a desire to build meaningful, long-lived systems and embrace ownership and ambiguity in an early-stage company.
• A collaborative team member with low ego and high standards.

Nice To Haves

• Working familiarity with core enterprise business processes (Quote-to-Cash, Procure-to-Pay, Hire-to-Retire) and ERP data.
• Experience with semantic modeling, metadata systems, or business-context modeling.
• Deep familiarity with enterprise integrations (SAP, Oracle, ServiceNow, Salesforce, Snowflake, Databricks).
• Prior founding-engineer or very-early-startup experience.

Responsibilities

• LLM orchestration and tool calling for agent reasoning over enterprise context and action.
• Developing agentic systems that observe signals, reason about decision patterns, and recommend or automate governed actions.
• Creating ontology generation pipelines to induce machine-readable models of enterprises from their systems and knowledge bases.
• Building embedding pipelines and knowledge graph integration for the semantic retrieval layer.
• Implementing operational memory systems to record events, decisions, actions, and outcomes for platform learning.
• Developing evaluation harnesses to score confidence, benchmark outcomes, and prove decision quality improvements.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: No Education Listed