Principal Applied AI Engineer

About the Role

We are hiring a Applied AI Engineer for a leading fintech company's AI Team to serve as the team's technical anchor in the United States.

You will lead two primary streams:

• AI Coding tooling and developer experience — bringing the engineering depth of Silicon Valley front-line teams (Claude Code, Cursor, Devin, Replit Agent, etc.) into ByLabs.
• AI application paradigm exploration and dogfooding — building small, frontier prototypes in internal scenarios that validate streaming UX, transparent agent steps, long-context memory, and other emerging patterns, and propagating them across the team through reference code, blog posts, and workshops.

This role is about craft and taste . You are not a platform architect, nor a BU project delivery engineer. You are the person who turns front-line Silicon Valley product engineering experience into multiplicative leverage for the entire AI Team.

Responsibilities

• Introduce AI Coding tooling best practices — Bring the engineering depth of Claude Code, Cursor, Devin, Replit Agent, and similar tools (Skills, hooks, subagents, long-context engineering, MCP integration) into ByLabs. Produce engineer onboarding playbooks and advanced-usage standards.
• Set the bar for the Skill Marketplace — Define Skill design conventions; personally deliver 5–10 reference-quality Skills as exemplars; raise team-wide Skill engineering quality through PR review.
• Prototype an AI-native engineering workflow — Reimagine the spec → design → implementation → review → testing → release → operations lifecycle around AI tools, producing a reference workflow APAC teams can adopt.
• Build internal AI application prototypes (employee-facing scenarios) — In OpenClaw, A2UI, role-bound AI assistants, and similar internal contexts, build small frontier prototypes that validate streaming UX, transparent agent steps, long-context memory, multi-agent collaboration, and other emerging patterns.
• Provide reference architecture code — When APAC teams face hard architectural choices in new AI scenarios, deliver runnable "this is how Silicon Valley does it" reference implementations — not documents, but working code.
• Cross-team craft propagation — One internal tech talk per month, one in-depth blog per quarter, and one onsite workshop in APAC per half year. Distill Silicon Valley AI application best practices into durable team assets.
• Architecture review participation — As the AI Team's anchor in the U.S., participate in ByLab's AI architecture review process and provide frontier perspective and taste-based feedback at the application layer.

Requirements

• Education: Top-tier CS / EE BS or above; MS preferred.
• 6+ years of software engineering experience, including at least 2 years focused on LLM applications.
• Senior AI application engineering experience: Has shipped AI applications from 0 → 1 in production (not demos). Must have at least one tour of duty as a core engineer at a top-tier Silicon Valley AI company or a leading AI product team — examples include Anthropic, OpenAI, Meta, and similar.
• Deep AI Coding tooling fluency: Claude Code, Cursor, Devin, or Replit Agent (at least one) is a daily-driver in your workflow, and you can articulate its engineering implementation. Strong understanding of the engineering tradeoffs in Skills, hooks, subagents, MCP, and long-context engineering.
• Agent application engineering depth: Solid grasp of ReAct, Plan-Execute, Reflection, Multi-Agent, and Orchestrator-Worker tradeoffs. Hands-on experience with LangGraph, AutoGen, CrewAI, OpenAI Swarm, or in-house frameworks.
• Strong full-stack engineering: Strong backend (Go / Python / TypeScript). Mid-level or above frontend (React / Next.js). Comfortable with end-to-end streaming rendering and interaction.
• Strong product sense and craft: Comfortable collaborating with PMs and designers; you have considered opinions and taste on AI application UX patterns (streaming, undo, context surfacing, agent-step progress, etc.).
• Public technical influence: A track record of public output — blog, talks, OSS contributions — sufficient to represent the team's craft externally.
• Self-direction and async collaboration: Capable of independently judging value priorities and driving prototype-to-dogfooding loops; effective at collaborating with APAC counterparts via documents, PRs, and asynchronous communication.

Nice to have

• Open-source contributions to LangChain, LlamaIndex, AutoGen, CrewAI, Vercel AI SDK, Claude Code MCP, OpenTelemetry GenAI, or similar projects.
• Track record of translating research output (papers, blog posts) into production application patterns.
• SaaS B2B product 0 → 1 experience.
• Experience productizing multilingual (English / Chinese) applications.
• AI experience in the financial or crypto domain.