Software Engineer, AI Agents

Blockit AI • San Francisco, CA

3h • Hybrid

About The Position

Blockit is building AI that fixes the coordination of time, an autonomous time agent that handles the full complexity of scheduling—timezones, group coordination, in-person logistics—like an executive assistant that never sleeps. Blockit is one of the first multiplayer, stateful AI agents—coordinating between multiple people, maintaining context across conversations, and taking real actions in the world. As more people connect their calendars, our network becomes exponentially more powerful. This is the foundation of a platform of AI agents with access to the world's time. The role involves owning the intelligence at the core of Blockit: our scheduling agents that autonomously coordinate meetings across people, time zones, and constraints. This includes designing and iterating on agent architectures, writing and refining prompts, building evaluation frameworks, and shipping new capabilities as models improve. The engineer will work across orchestrator agents (which manage conversation flow) and specialized sub-agents, with the goal of making Blockit smarter, faster, and capable of handling increasingly complex coordination problems. The role involves architecting and building real-world AI agents used in production.

Requirements

• 2+ years of experience shipping and owning production software
• Strong backend engineering skills, with the ability to work across the stack when needed
• Experience working with LLMs in production systems (or a demonstrated ability to learn quickly in this space)
• Deep curiosity about agent architectures and how the industry is evolving beyond simple prompt-based systems
• Clear, structured communicator who can explain what’s working, what isn’t, and why

Responsibilities

• Write and refine prompts across our agent system—orchestrators, sub-agents, and tools
• Build and maintain evals to measure agent quality and catch regressions
• Debug agent failures: figure out why it misunderstood a request or made a bad call
• Implement new agent capabilities as user needs expand
• Experiment with new architectures and techniques as models improve
• Instrument and analyze agent behavior to find patterns and failure modes

What This Job Offers

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