Architect AI Agents – Design, orchestrate, and deploy robust AI agent architectures, including multi-agent systems, reasoning frameworks, and dynamic tool-use capabilities (RAG, APIs) to automate complex business workflows and analytics.
Develop Agent Harnesses & Evaluation Pipelines – Build and maintain robust testing harnesses (Agent Harness), simulation environments, and CI/CD pipelines to rigorously evaluate agent performance, safety, reasoning logic, and tool-calling accuracy before production deployment.
Collaborate & Innovate – Work closely with cross-functional teams to identify opportunities, gather requirements, and transform business challenges into scalable, agentic AI solutions.
Build Robust Systems – Partner with data engineers and platform architects to implement high-performance, real-time GenAI applications. Ensure robust state management, secure memory handling, safety guardrails, and low-latency decisioning.
Explore & Evolve – Stay at the forefront of LLM advancements and agentic frameworks (e.g., LangChain, LlamaIndex, AutoGen, Semantic Kernel). Continuously research and implement new paradigms in AI reasoning, planning, and evaluation to refine the team’s capabilities.
Communicate Insights – Present complex agent architectures and GenAI strategies to business stakeholders and executives, ensuring technical innovations translate into meaningful business outcomes.
Minimum Qualifications
AI & Agent Architecture: Deep understanding of Large Language Models (LLMs), prompt engineering, and hands-on experience building autonomous agents or multi-agent orchestration frameworks.
LLMOps & Agent Harness: Practical experience building agent evaluation harnesses, automated testing frameworks, and monitoring pipelines to track hallucination rates, safety metrics, and overall LLM reliability.
System Design: Proven experience in designing scalable software systems, integrating LLMs with external environments (APIs, databases, enterprise tools), and managing complex conversational state/memory.
Machine Learning: Understanding of common machine/deep learning algorithms and practical experience in one or more of the following areas: time series forecasting, anomaly detection, convex optimization, computer vision, NLP, LLM, recommendation system, and Auto ML.
Programming Language: Strong ability to implement AI pipelines and scalable applications in Python (essential), along with familiarity in Scala, Java, or C++.
Communication & Presentation: Superior verbal and written communication skills, with the ability to convey meticulous architectural concepts and AI considerations to non-experts.
Databases: Solid understanding of relational databases (SQL), vector databases for RAG applications, and large-scale distributed systems.
PhD in Computer Science, Artificial Intelligence, Machine Learning, or related field; or PhD in Math, Engineering, Economics, or hard science with AI/data science fellowship; or M.S. in a related field with strong industry experience applying LLMs and AI agent architectures to real business problems.
Preferred Qualifications
Advanced Agentic Patterns: Familiarity with advanced reasoning and planning paradigms (e.g., ReAct, Chain-of-Thought, Tree-of-Thoughts) and experience in building evaluation frameworks/sandboxes for generative systems.
Insight: Ability to extract meaningful business insights from complex data interactions and identify the stories behind the patterns.
Creativity: A drive to engineer novel features, design innovative agent tools, and push beyond current off-the-shelf LLM approaches.
Bilingual: Excellent verbal and written communication skills, in both Mandarin Chinese and English.