Applied AI Engineer

Location

Jackson Square, San Francisco

Fully on-site, 5 days a week

Above-market base equity benefits

Sponsorship available only for candidates already in the United States

As an Applied AI Engineer, you’ll help architect the foundation of next-generation Mind Architecture, the system that powers how digital minds learn, reason, and express individuality.

Unlike traditional RAG systems that treat data as a static collection of documents, we build rich, hierarchical knowledge graphs that mirror how real experts think capturing not just facts, but relationships, reasoning styles, and conceptual depth.

You’ll work at the intersection of graph systems, LLM reasoning, and scalable AI infrastructure, bringing together symbolic structure and neural intelligence to redefine how knowledge lives digitally.

• Design and evolve the graph-based architecture that models a mind’s reasoning, associations, and conceptual hierarchies.
• Develop novel embeddings and contextual retrieval methods that make each mind distinct not just accurate, but alive.
• Build next-generation retrieval-augmented generation systems that integrate structured graph reasoning with neural retrieval.
• Implement and refine LLM evaluation frameworks to ensure each mind improves over time in quality, consistency, and individuality.
• Push the performance of frontier LLMs through advanced prompt engineering, dynamic context shaping, and evaluation-driven iteration.
• Architect efficient, low-latency inference pipelines for thousands of simultaneous mind interactions.
• Bridge ML systems and product engineering shipping AI-powered features that shape user experience directly.
• Translate abstract research ideas into robust, scalable production systems powering thousands of live digital minds.
• Define success metrics for “mind quality” advancing tone, style transfer, and reasoning fidelity.
• Build systems that continuously refine a digital mind’s authenticity and expressiveness.

• 4-6 years of experience in AI or ML engineering, with at least 12 years hands‑on with LLMs in production.
• Proven track record of building and deploying ML-powered systems that directly impact end‑user experience.
• Strong Python expertise, including asynchronous programming, event loop optimization, and performance tuning.
• Experience with retrieval-augmented generation (RAG), context engineering, and LLM eval frameworks.
• Deep practical understanding of how LLMs reason, how to structure inputs, and how to measure improvement.

• Experience with graph databases or graph-based retrieval (Neo4j, Arango
  
  DB, or custom-built graph layers).
• Background in document understanding, embeddings, or multimodal context assembly.
• Familiarity with AWS, distributed systems, and scalable backend architecture.
• Hands‑on experience fine‑toning LLMs or building adapters for tone/style adaptation.

• You thrive on hard problems and are motivated by impact over title.
• You’re comfortable building at the intersection of research, product, and systems engineering.
• You have an engineer’s rigor, a creator’s imagination, and a philosopher’s curiosity.

• Unlimited Learning Stipend: books, courses, or conferences of your choice.
• Comprehensive Health, Dental, and Vision coverage.
• 401(k) via Human Interest.
• Relocation assistance to San Francisco (if applicable).
• A creative, high-agency culture that celebrates curiosity and deep thinking.