Delphi
Overview
Why Delphi? At Delphi, we are redefining how knowledge is shared by creating a new medium for human communication: interactive digital minds that people can talk to, learn from, and be guided by. The Role
As part of our AI team, you will architect and implement improvements to the backbone of our Delphi mind architecture. The architecture is powered by knowledge graphs that capture information about the person as well as their associations, reasoning patterns, and conceptual frameworks that make each mind unique. Unlike traditional RAG systems that treat knowledge as a flat collection of documents, we’re building rich, hierarchical representations that mirror how human experts think and reason. What You\'ll Do
Graph Architecture & Design: design scalable knowledge graph architectures, develop novel embeddings to capture nuanced relationships, and build efficient indexing and retrieval for real-time querying. Evals for the Mind: defining the core components of the human mind, building strong mind architectures, giving customers confidence their minds improve over time, and advancing tone and style transfer to better reflect individuality. RAG System Innovation: build next-generation RAG systems that merge graph-based reasoning with neural retrieval and include robust evaluation frameworks to optimize quality across query types. Infrastructure & Scaling: scale infrastructure to support distributed, low-latency graph operations across thousands of instances with comprehensive monitoring and debugging tools. What You Bring
LLM Expertise & Application: deep understanding of how LLMs work with proven ability to apply them effectively, push their performance, and optimize through advanced prompt engineering techniques. Python Performance Mastery: strong experience with Python beyond surface level—expert with asynchronous programming, event loop optimization, and performance tuning for high-scale applications. RAG & Context Engineering: hands-on experience with retrieval-augmented generation, context engineering, and evaluation frameworks for LLM performance optimization. ML Engineering Bridge: skilled traditional software engineer with deep familiarity in ML/AI systems—you understand both the engineering and AI sides without needing a research background. Systems & Product Focus: ability to architect scalable backend systems while building AI-powered features that directly impact user experience and product outcomes. Bonus: Previous experience with graph-based retrieval and graph systems, AWS and cloud infrastructure understanding, and hands-on experience fine-tuning models. Why You\'ll Love It Here
We work on hard problems. Our team is full of former founders, and entrepreneurial individuals who are taking on immense initiatives. There is extreme upside. Very competitive salary and equity in a company on a breakout trajectory. We push each other. Work from our beautiful Jackson Square office in San Francisco, surrounded by peers pushing to do their best work. Benefits
Unlimited Learning Stipend: Whether it’s books, courses, or conferences, we want to support your growth and development. The more you learn and improve your craft the more effective we will be together. Health, Dental, Vision: Comprehensive coverage to keep to take care of your health. 401k covered by Human Interest. Relocation support to SF (as needed) Compensation
Compensation Range: $200K - $350K Additional
Seniority level: Mid-Senior level Employment type: Full-time Job function: Engineering and Information Technology Industries: Technology, Information and Internet
#J-18808-Ljbffr
Why Delphi? At Delphi, we are redefining how knowledge is shared by creating a new medium for human communication: interactive digital minds that people can talk to, learn from, and be guided by. The Role
As part of our AI team, you will architect and implement improvements to the backbone of our Delphi mind architecture. The architecture is powered by knowledge graphs that capture information about the person as well as their associations, reasoning patterns, and conceptual frameworks that make each mind unique. Unlike traditional RAG systems that treat knowledge as a flat collection of documents, we’re building rich, hierarchical representations that mirror how human experts think and reason. What You\'ll Do
Graph Architecture & Design: design scalable knowledge graph architectures, develop novel embeddings to capture nuanced relationships, and build efficient indexing and retrieval for real-time querying. Evals for the Mind: defining the core components of the human mind, building strong mind architectures, giving customers confidence their minds improve over time, and advancing tone and style transfer to better reflect individuality. RAG System Innovation: build next-generation RAG systems that merge graph-based reasoning with neural retrieval and include robust evaluation frameworks to optimize quality across query types. Infrastructure & Scaling: scale infrastructure to support distributed, low-latency graph operations across thousands of instances with comprehensive monitoring and debugging tools. What You Bring
LLM Expertise & Application: deep understanding of how LLMs work with proven ability to apply them effectively, push their performance, and optimize through advanced prompt engineering techniques. Python Performance Mastery: strong experience with Python beyond surface level—expert with asynchronous programming, event loop optimization, and performance tuning for high-scale applications. RAG & Context Engineering: hands-on experience with retrieval-augmented generation, context engineering, and evaluation frameworks for LLM performance optimization. ML Engineering Bridge: skilled traditional software engineer with deep familiarity in ML/AI systems—you understand both the engineering and AI sides without needing a research background. Systems & Product Focus: ability to architect scalable backend systems while building AI-powered features that directly impact user experience and product outcomes. Bonus: Previous experience with graph-based retrieval and graph systems, AWS and cloud infrastructure understanding, and hands-on experience fine-tuning models. Why You\'ll Love It Here
We work on hard problems. Our team is full of former founders, and entrepreneurial individuals who are taking on immense initiatives. There is extreme upside. Very competitive salary and equity in a company on a breakout trajectory. We push each other. Work from our beautiful Jackson Square office in San Francisco, surrounded by peers pushing to do their best work. Benefits
Unlimited Learning Stipend: Whether it’s books, courses, or conferences, we want to support your growth and development. The more you learn and improve your craft the more effective we will be together. Health, Dental, Vision: Comprehensive coverage to keep to take care of your health. 401k covered by Human Interest. Relocation support to SF (as needed) Compensation
Compensation Range: $200K - $350K Additional
Seniority level: Mid-Senior level Employment type: Full-time Job function: Engineering and Information Technology Industries: Technology, Information and Internet
#J-18808-Ljbffr