Location: San Francisco, CA (In-person)

On-site | Full-time

Compensation: $130K - $170K / 0.5% - 1.5%

Our client is a venture-backed startup based in San Francisco that is revolutionizing the corporate events industry through an AI-powered platform. By automating the complexities of venue sourcing and vendor negotiations, the organization enables teams to connect in person more efficiently than ever before. Having already executed global events for some of the world’s most recognizable technology companies, our client is now scaling its engineering team to push the boundaries of autonomous AI workflows.

This role is designed for a founding-level AI Engineer who thrives in a "zero-to-one" environment. The successful candidate will be responsible for building and scaling the AI systems that automate event planning end-to-end, moving beyond simple chatbots to create sophisticated, autonomous agents capable of real-world execution.

Key Responsibilities

• System Architecture: Build and scale AI systems that automate complex event planning workflows, from initial research to final execution.
• Agent Development: Design and deploy AI agents specialized in auto-emailing, calling, web scraping, and deep research.
• Optimization: Implement techniques to improve accuracy and reduce hallucinations in LLM-powered features.
• Workflow Design: Create scalable AI workflows utilizing modern LLM frameworks and tools.
• Performance Validation: Develop robust evaluation systems to measure, monitor, and improve AI performance over time using real customer data.
• Cross-Functional Collaboration: Partner closely with Product and Operations teams to identify automation opportunities and ship high-impact features.
• Foundational Engineering: Shape the firm’s AI/ML architecture and engineering practices from the ground up.

Requirements

• AI/LLM Expertise: Proven experience building and deploying AI/LLM systems in a production environment.
• Technical Proficiency: Advanced skills in Python and familiarity with modern frameworks such as LangChain or LlamaIndex.
• Advanced Techniques: Deep understanding of prompt engineering, Retrieval-Augmented Generation (RAG), and methods to enhance LLM reliability.
• Autonomous Systems: Hands-on experience with AI agents, tool calling, and autonomous system design.
• Full-Stack Capabilities: Ability to handle full-stack development to ship features end-to-end.
• Environment: Comfort moving fast, experimenting, and iterating based on real-world feedback in an ambiguous startup setting.
• Location: This is an in-person role based in San Francisco.

Preferred Qualifications

• Experience building AI web agents or browser automation systems.
• Early-stage (0-to-1) AI product development experience.
• Familiarity with AI observability tools and evaluation frameworks.
• Contributions to open-source AI projects or published research.

Benefits

• Compensation: Salary range of $130,000 – $170,000 with 0.5% – 1.5% equity.
• Health & Wellness: Comprehensive health insurance, a monthly fitness stipend, and 12 weeks of paid parental leave.
• In-Office Perks: Daily free lunch and dinner provided at the San Francisco office.
• Travel & Culture: Quarterly team offsites (previous locations include premier international destinations) and exclusive access to top-tier venues and events.
• Time Off: Generous PTO policy with structured "required time off" to ensure sustainable high performance.
• Ownership: High levels of autonomy, direct access to the founding team, and the opportunity to influence the core product direction.