Senior AI Engineer

About the Role

We are looking for a Senior AI Engineer to design, build, and ship AI-powered capabilities for our enterprise platforms — including AI agents, copilots, and intelligent automation embedded in real business workflows (e.g., billing operations, service management, customer onboarding).

This is a builder role, not a research role. We expect you to be fluent with modern AI-assisted development tools, but that alone is not enough: you must have shipped AI agents or AI applications to real users and understand what it takes to make LLM-based systems reliable, safe, and maintainable in production.

This role will be hybrid in our Morrisville, NC office!

Key Responsibilities

AI Application & Agent Development

• Design and implement AI agents and LLM-powered applications: task decomposition, tool/function calling, multi-step orchestration, and human-in-the-loop workflows
• Build RAG pipelines and knowledge systems: document ingestion, chunking, embedding, retrieval strategy, and grounding quality
• Integrate LLM capabilities with enterprise systems via APIs, event-driven architecture, and middleware; handle auth, rate limits, and failure modes
• Design prompt/context architectures that are versioned, testable, and maintainable — not one-off prompt hacking

Production Engineering & Quality

• Build evaluation frameworks for AI features: golden datasets, automated eval pipelines, regression testing for prompt/model changes
• Implement guardrails and safety controls: input/output validation, hallucination mitigation, PII handling, and audit logging
• Own observability for AI systems: tracing, token/cost monitoring, latency optimization, and model fallback strategies
• Make pragmatic model and architecture choices (hosted APIs vs. self-hosted, model selection, caching, fine-tuning vs. prompting) based on cost, latency, and quality trade-offs

Collaboration & Enablement

• Partner with product analysts and business stakeholders to turn ambiguous AI use cases into scoped, buildable solutions
• Establish engineering best practices for AI-assisted development (Claude Code, Cursor, Copilot, etc.) across the team
• Mentor engineers on agent design patterns, evaluation discipline, and responsible AI practices

Basic Qualifications

• Bachelor's degree or above in Computer Science, Software Engineering, or related field
• 5+ years of software engineering experience, with 2+ years building LLM-based applications or AI agents

Preferred Qualifications

• Strong preference for fluency in Mandarin
• At least one AI agent or AI application shipped to production with real users — you can walk us through the architecture, the failure modes you hit, and how you addressed them.
• Hands-on depth in the modern AI stack:
  • LLM APIs (Anthropic, OpenAI, or equivalent) including tool use / function calling and structured outputs
  • Agent frameworks or hand-rolled orchestration (e.g., LangGraph, MCP-based tooling, or custom-built agent loops) — and clear opinions on when a framework is the wrong choice
  • RAG and vector search (embedding models, vector databases, retrieval evaluation)
• Strong general engineering fundamentals: Python and/or TypeScript, API design, testing, CI/CD, and version control — AI tools accelerate you, but your code must stand on its own without them
• Experience with evaluation and observability for non-deterministic systems

• Experience embedding AI features into enterprise systems (ERP, billing, ITSM/ServiceNow, CRM) rather than standalone consumer apps
• Familiarity with Model Context Protocol (MCP) or building tool integrations for agents
• Experience with fine-tuning, model distillation, or self-hosted open-weight models (vLLM, etc.)
• Knowledge of enterprise AI governance: data privacy, compliance constraints, model risk management
• Cloud platform experience (AWS Bedrock, Azure OpenAI, GCP Vertex AI)
• Contributions to open-source AI projects, or a public portfolio of shipped AI work