CareerPlanGet AI match score →

Ai Agent Developer

🌐 Remote💼 Full-time🗓 2026-07-31

Core

Build production AI agents and reference stacks for voice, browsing, and scraping frameworks, serving agent operators and integrators.

Role type

Senior IC AI Agent Developer

Builds

Production agent stacks, SDKs, quickstarts, and agent-awareness primitives for voice, browsing, and scraping frameworks.

Domain

AI Agents / Autonomous Agents / Spend Management Infrastructure

Deliverable

production ML models | product features

Required skills

TypeScript, Python, async programming, streaming, tool-calling, LLM tool use, MCP (Model Context Protocol), REST integration, SDK development, error handling, retry logic, budget management, technical writing.

Preferred skills

DevRel, solutions engineering, open-source contributions, published agent content.

Technologies

TypeScript, Python, CrewAI, LangChain, MCP, REST, USDC.

Responsibilities

Build production agents on top of Floe, ship reference agent stacks for voice/browsing/scraping, own end-to-end developer experience (quickstarts, tools, error-matrix), run agent circuits daily, pair with integrators on their first agent.

Seniority

Senior, hands-on IC

Rewrite
## About the role Build production agents on top of Floe. You'll be both a customer of and contributor to our SDKs. Ship reference agent stacks for the frameworks our users live in: voice, browsing, scraping Own end-to-end developer experience: quickstarts, MCP tools, error-matrix + retry semantics, agent-awareness primitives Run agent circuits daily. Surface what's broken or missing for real autonomous use cases. Close the loop with protocol + infra. Pair directly with prospective integrators on their first agent — help them get from bank account to first x402 call in under a session. ## You probably have Shipped agents in production (or in a serious side project) — not just demos. You've felt the pain of pre-funding, brittle tool calls, and decision loops that don't know their own budget. Strong TypeScript and/or Python. Comfortable in async, streaming, tool-calling, and at least one agent framework end-to-end. A working mental model of LLM tool use, MCP, and the tradeoffs between SDK / MCP / REST integration paths. Strong writing. You can turn a 30-minute integration session into a quickstart that the next 100 devs follow without help. ## Bonus DevRel, forward-deployed, or solutions-engineering background at an API-first company. Published agent content (blog, video, OSS) that other devs actually use. ## Why now Agents are starting to spend real money. Almost every team building one is hand-rolling pre-funded wallets, custom retry logic, and spend caps that the model can't see. Floe replaces that with a credit primitive. If you want to be the person who defines what "good" looks like for agent money infra, this is the seat. ## Compensation Competitive salary + meaningful equity + USDC option. Remote-first, async-default. ## How to Apply Step 1 is dogfood gate. Send us: - What your agent does. one paragraph. how does it pay? what APIs does it use, if any? - https://github.com/Floe-Labs/floe-guard/ star and try an agent circuit you've shipped (link or 60-sec Loom is fine) . this is free no deppsit required. - 2–3 things you wish your agent's spend layer did differently. - Your framework: CrewAI LangChain, custom, etc. - Star our repo https://github.com/Floe-Labs/floe-guard/
Sourced via wellfound · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
Apply on Wellfound ↗