Staff Backend Engineer, AI

🚂About Pulley

Pulley's mission is to make it easier for anyone to start a company. We believe that more startups should exist and that founder-led companies are more successful in the long term. With Pulley’s cap table management tools, companies can better understand and optimize their equity for the long term. Starting a company is hard enough. Managing equity shouldn’t be. 

We’re a high-performing team on a mission to redefine how early-stage leaders build and manage their companies in an AI-native world. As AI reshapes how businesses operate, we see a unique opportunity to reimagine equity and business management from the ground up. A brand-new, unsolved challenge that we’re excited to tackle.

Pulley is growing quickly with over 4,000 customers, including startups like Linear, Runway, Fathom, and Roam. Our trajectory is fueled by top investors like Founders Fund, Stripe, General Catalyst, Caffeinated Capital, 8vc, Elad Gil, and other incredible angels. All of our growth has been organic, and we’re expanding the team to meet the growing demand.

We’re looking for passionate, execution-focused self-starters to help us build the next generation of tools for founders.

🌟 About the role

We're looking for a Staff Backend Engineer who will architect and build the foundational systems powering our AI-native product. You'll own the design and implementation of scalable backend services that enable intelligent agents to automate complex equity workflows. This is a 0-1 opportunity where you'll define service boundaries, design APIs, and build the distributed systems that make AI capabilities production-ready and reliable at scale.

In this high-impact role, you'll work directly with leadership to shape our technical strategy and establish architectural patterns that will guide our engineering organization as we scale.

🛠 What You’ll Do

• Architect distributed systems that power AI agent orchestration, handling complex multi-step workflows with reliability and observability
• Design and implement core backend services in Golang for high-performance, concurrent operations and Python for AI/ML integrations and data pipelines
• Build robust APIs and service interfaces that abstract AI capabilities for consumption by multiple clients and internal systems
• Own the technical roadmap for backend infrastructure supporting LLM integrations, vector search, and real-time data processing
• Establish architectural patterns and standards for service design, data modeling, and inter-service communication
• Drive system scalability and reliability, implementing caching strategies, database optimization, and async processing patterns
• Build data pipelines that process equity data, embeddings, and user interactions to continuously improve AI model performance
• Collaborate cross-functionally to translate business requirements into technical architecture and make pragmatic build vs. buy decisions
• Mentor engineers on backend best practices, system design, and technical decision-making

🙌 What You Bring

• Technical Foundation:

  • 7+ years of backend engineering experience building production systems at scale
  • Expert-level proficiency in Python for AI/ML integrations, data processing, and scripting
  • Strong Python skills with deep understanding of concurrency patterns, performance optimization, and production Go services
  • Proven experience designing and building distributed systems, including microservices architecture, event-driven systems, and async workflows
  • Deep knowledge of API design (REST) and service-to-service communication patterns

  AI Infrastructure Experience:

  • Demonstrated experience building backend systems that integrate LLMs and AI capabilities into production applications
  • Hands-on work with agent frameworks, LLM orchestration, and AI service reliability
  • Familiarity with RAG architectures, vector databases (Pinecone, Weaviate, Qdrant), and embeddings pipelines
  • Experience building evaluation frameworks and observability for AI systems
  • Understanding of prompt engineering and LLM API optimization (latency, costs, rate limits)

  System Design & Leadership:

  • Track record of architecting greenfield services from concept to production with scalability and maintainability in mind
  • Experi