AI Agentic Trading Expert

CoinMarketCap; Hong Kong; On-site; HKD 120,000 - 180,000; Full time

Job summary

CoinMarketCap is seeking an experienced engineer to design and ship official skills across our 14-domain taxonomy, from Leverage to DeFi primitives. You will define publishing standards, SDK ergonomics, and the revenue model for third-party developers, while owning the MCP server and CLI to simplify skill authoring.

You will drive agent-side integrations, partner with teams to embed CMC skills in live products, and contribute to ecosystem events with hackathons and technical content.

Qualifications

• Crypto-native fluency: explain DEX AMMs, perp funding, bridge risk, and on-chain identity without Google.
• Hands-on AI agent systems: function calling, tool use, MCP, LangGraph/OpenClaw in production.

Responsibilities

• Design and ship the official skills spanning our 14-domain taxonomy (Leverage, Assets, Portfolio, Pulse, Plays, Risk, etc.).
• Define publishing standards, SDK ergonomics, and the skill-signing / revenue-share contract for third-party developers.
• Own the MCP server and CLI that make skill authoring feel as easy as writing a Vercel function.
• Partner with teams to land CMC for Agent skills inside live agent products.
• Implement A2A / cross-agent protocol adapters for discoverable skills.
• Feed integration learnings back into the SDK with docs/pages or helper APIs.
• Co-design and run CMC for Agent hackathons with tracks, bounties, reference repos, and judging rubrics.
• Write technical content to attract developers: launch posts, recipes, walkthroughs, and build-with-us threads.
• Be the technical face at Web3 × AI events.
• Improve LLM grounding for crypto context to reduce hallucinations and latency.
• Build evaluation harnesses for skill accuracy, reliability, and economic honesty.

Skills

Crypto-native fluency

AI agent systems

Developer-product instincts

Tools

LangGraph

OpenClaw

Job description

Key Responsibilities

• Design and ship the official skills spanning our 14-domain taxonomy (Leverage, Assets, Portfolio, Pulse, Plays, Risk, etc.) — covering market analysis, on-chain liquidity, identity resolution, derivatives, and DeFi primitives.
• Define publishing standards, SDK ergonomics, and the skill-signing / revenue-share contract that third-party developers will build against.
• Own the MCP server and CLI that make skill authoring feel as easy as writing a Vercel function.

Build The Capabilities Market (Supply Side)

• Design and ship the official skills spanning our 14-domain taxonomy (Leverage, Assets, Portfolio, Pulse, Plays, Risk, etc.) — covering market analysis, on-chain liquidity, identity resolution, derivatives, and DeFi primitives.
• Define publishing standards, SDK ergonomics, and the skill-signing / revenue-share contract that third-party developers will build against.
• Own the MCP server and CLI that make skill authoring feel as easy as writing a Vercel function.

Drive Agent‑Side Integrations (Demand Side)

• Partner with teams to land CMC for Agent skills inside live agent products.
• Implement A2A / cross-agent protocol adapters so a skill published once is discoverable and callable everywhere agents live.
• Feed integration learnings back into the SDK — every painful integration becomes a docs page or a helper API.

Grow the Developer Community (Ecosystem & Hackathons)

• Co‑design and run CMC for Agent hackathons — tracks, bounties, reference repos, judging rubrics, and the technical support Discord during event weekends. Deep collaboration expected with BNB Hack Local Series, YZi Labs EASY Residency, and Virtuals/ACP ecosystem events.
• Write the technical content that makes developers choose us: launch posts, cookbook recipes, video walkthroughs, and "build-with-us" threads.
• Be the technical face at Web3 × AI events.

Engineering & Grounding

• Improve LLM grounding on crypto‑specific context (tokens, contracts, narratives) to cut hallucination and latency on trading‑adjacent queries.
• Build evaluation harnesses that measure skill accuracy, reliability, and economic honesty — not just latency and uptime.

Requirements

• Crypto‑native fluency: you can explain DEX AMMs, perp funding, bridge risk, and on‑chain identity without reaching for Google. Comfortable reading Solidity even if you don't write it daily.
• AI agent systems, hands‑on: function calling, tool use, MCP, and at least one of LangGraph / OpenClaw in production — not just tutorials.
• Developer‑product instincts: you've built or heavily contributed to an SDK, CLI, or API that outside developers actually adopted — and you have opinions about why most developer docs are bad.