As a backend engineer, I mainly worked on the planning and execution part of the agent system. Once a research request comes in, this component breaks the work into smaller steps, tracks which steps are running or completed, and handles failures or retries. My focus was making that workflow reliable, especially for long-running research tasks.
Hechao Li
@hechaoli
I build scalable AI, search, and distributed systems powering millions of requests.
What I'm looking for
At OpenAI, I lead backend architecture for the Deep Research API, building distributed agent orchestration, document ingestion, vector retrieval, RAG, and LLM observability systems for citation-backed research across web-scale and enterprise data.
Previously at Netflix, I built LLM-integrated conversational search and personalized ranking infrastructure with sub-second serving performance. At Facebook, I developed transaction, consensus, execution, and storage systems for Diem, and at VMware Wavefront, I built high-scale time-series ingestion, analytics, and anomaly detection platforms.
Experience
Work history, roles, and key accomplishments
Led backend architecture for a distributed agent orchestration system, designing DAG-based planning and fault-tolerant workflows. Built scalable document ingestion and vector retrieval pipelines for large-scale semantic search.
Education
Degrees, certifications, and relevant coursework
Carnegie Mellon University
Master of Science, Computer Science
2015 - 2016
Pursued a Master's degree in Computer Science at Carnegie Mellon University from 2015 to 2016.
Availability
Location
Authorized to work in
Job categories
Skills
Interested in hiring Hechao?
You can contact Hechao and 90k+ other talented remote workers on Himalayas.
Message HechaoGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
