Startups · AI

Member of Technical Staff: Agent Runtime

ego · San Francisco, CA, US / Remote (Tokyo, JP; SG) · Remote

← All jobs
About ego

AI applied research lab building synthetic sapience; human-like AI. Backed by Y Combinator.

About the role

Ego AI is a YC-backed applied AI research lab building the behavioral infrastructure for AI companions and agents. We work at the intersection of real-time conversational instincts, memory, and persistent identity; the layer that makes AI feel genuinely alive. We're a small, fast-moving team and we're defining a new category of human-AI interaction.

What they're looking for

  • 3+ years building backend or infrastructure systems, with real production ownership of stateful services or relevant projects that they have worked on
  • Hands-on experience building LLM agent systems: tool-calling loops, defensive handling of model output, and step/token/cost budgets
  • Deep grasp of durable execution: checkpointing, idempotency, outbox/step-log patterns, and the ability to reason precisely about failure windows (what if it dies after the side effect but before it is recorded?)
  • A deliberate context-management strategy for long-horizon tasks, and the ability to defend its trade-offs rather than only describe it
  • Strong API and data-model design, persistence behind clean seams, comfort being judged on docker compose up working cold from a README
  • Clear written communication. Architecture docs a reviewer understands before reading the code. Honest scoping (what you cut and why)
More about this role

Member of Technical Staff: Agent Runtime (Ego) Location: San Francisco, CA (hybrid) · Reports to: Founding team

Ego AI is a YC-backed applied AI research lab building the behavioral infrastructure for AI companions and agents. We work at the intersection of real-time conversational instincts, memory, and persistent identity; the layer that makes AI feel genuinely alive. We're a small, fast-moving team and we're defining a new category of human-AI interaction.

Own the agent harness. Design and maintain our core agentic loop (plan → tool call → observe → repeat → finalize) as a small, legible state machine. Errors are first-class: malformed tool calls, hallucinated tool names, and throwing tools get fed back to the model. They never crash the loop.

Make execution durable. Build checkpointed, resumable sessions backed by a database: step logs with pending/committed status, idempotency keys on side-effecting tools, and a clear account of the at-least-once vs exactly-once boundary. A crash between the LLM call and the tool call, or mid-compaction, must never corrupt a session or double-fire a POST.

Solve long-horizon context. Own our compaction strategy: pinned goals, running...

Read the full posting on ego's site ↗

Engineering

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.