Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hechao Li is a Senior/Staff Software Engineer specializing in AI platforms, distributed systems, cloud infrastructure, and backend engineering. He has experience building production-scale AI applications, LLM-powered agent systems, data platforms, and scalable cloud-native services at companies including OpenAI, Meta, Google, and other technology organizations. His expertise spans Python, Go, Java, Kubernetes, AWS/Azure/GCP, RAG pipelines, agent orchestration, and enterprise AI infrastructure. He is passionate about building reliable systems that combine strong software engineering fundamentals with emerging AI technologies.…Hechao Li is a Senior/Staff Software Engineer specializing in AI platforms, distributed systems, cloud infrastructure, and backend engineering. He has experience building production-scale AI applications, LLM-powered agent systems, data platforms, and scalable cloud-native services at companies including OpenAI, Meta, Google, and other technology organizations. His expertise spans Python, Go, Java, Kubernetes, AWS/Azure/GCP, RAG pipelines, agent orchestration, and enterprise AI infrastructure. He is passionate about building reliable systems that combine strong software engineering fundamentals with emerging AI technologies.

Hechao Hechaoli

Software Engineer, Back-End Developer, AI Engineer, +2





Hechao Li is a Senior/Staff Software Engineer specializing in AI platforms, distributed systems, cloud infrastructure, and backend engineering. He has experience building production-scale AI applications, LLM-powered agent systems, data platforms, and scalable cloud-native services at companies including OpenAI, Meta, Google, and other technology organizations. His expertise spans Python, Go, Java, Kubernetes, AWS/Azure/GCP, RAG pipelines, agent orchestration, and enterprise AI infrastructure. He is passionate about building reliable systems that combine strong software engineering fundamentals with emerging AI technologies.…Hechao Li is a Senior/Staff Software Engineer specializing in AI platforms, distributed systems, cloud infrastructure, and backend engineering. He has experience building production-scale AI applications, LLM-powered agent systems, data platforms, and scalable cloud-native services at companies including OpenAI, Meta, Google, and other technology organizations. His expertise spans Python, Go, Java, Kubernetes, AWS/Azure/GCP, RAG pipelines, agent orchestration, and enterprise AI infrastructure. He is passionate about building reliable systems that combine strong software engineering fundamentals with emerging AI technologies.

Available to hire

Hechao Li is a Senior/Staff Software Engineer specializing in AI platforms, distributed systems, cloud infrastructure, and backend engineering. He has experience building production-scale AI applications, LLM-powered agent systems, data platforms, and scalable cloud-native services at companies including OpenAI, Meta, Google, and other technology organizations. His expertise spans Python, Go, Java, Kubernetes, AWS/Azure/GCP, RAG pipelines, agent orchestration, and enterprise AI infrastructure. He is passionate about building reliable systems that combine strong software engineering fundamentals with emerging AI technologies.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

Javanese

Advanced

Work Experience

Member of Technical Staff at OpenAI

June 1, 2025 - Present

Enterprise-scale autonomous agent platform and LLM orchestration for deep research workflows. Led backend architecture for distributed agent orchestration using Agents SDK and DAG-based planning/execution with fault-tolerant long-running AI tasks. Built scalable document ingestion pipelines (PDF/HTML, OCR, chunking, embeddings) for semantic indexing. Developed low-latency vector retrieval across millions of chunks using embedding models and vector databases. Implemented recursive agent reasoning loops combining LLM planning, tool invocation, and feedback-driven query refinement. Delivered RAG pipelines integrating retrieval, summarization, and synthesis for citation-grounded outputs. Added context-window optimization via hierarchical summarization/ranking to respect token constraints. Implemented production-grade LLM orchestration leveraging GPT-4.5/o3 with structured outputs, tool usage, and multi-step reasoning. Improved reliability with retrieval validation, citation verification, a

Senior Software Engineer at Netflix

May 1, 2022 - May 1, 2025

Built LLM-powered conversational search and ranking systems transforming Netflix discovery into natural language experiences. Led backend development of LLM-integrated search orchestration services including intent extraction, query rewriting, and conversational refinement. Designed RAG pipelines combining LLM query understanding with semantic retrieval over large-scale content embeddings. Built scalable vector search using Faiss/OpenSearch for approximate nearest-neighbor retrieval over millions of embeddings. Developed distributed content ingestion pipelines using Maestro and processing scripts for subtitles and metadata to embeddings and knowledge-graph features. Implemented Unifed Contextual Ranker (UniCoR) inference combining user behavior, query context, and content signals for personalized ranking. Designed microservices query pipelines using Java/Spring Boot with REST/gRPC APIs and service mesh routing for high availability. Built feature engineering pipelines integrating knowl

Software Engineer at RBC / Die m (Libra)

October 1, 2018 - May 1, 2022

Contributed to permissioned BFT blockchain infrastructure enabling global payments with distributed validator nodes, deterministic execution, and cryptographically verifiable state. Designed distributed transaction processing pipelines spanning admission control, mempool propagation, consensus, execution, and storage layers. Built JSON-RPC admission services for transaction validation, signature verification, and stateless pre-check enforcement. Developed shared mempools with gossip protocol to ensure consistent transaction propagation across validator nodes. Implemented Die m BFT consensus (HotStuff-based) for fault-tolerant agreement under Byzantine conditions. Built execution pipeline using MoveVM ensuring deterministic state transitions and preventing double-spending. Designed storage layer (Die mDB) on RocksDB with Merkle tree-based authenticated state and versioned ledger. Optimized consensus throughput and latency via batching, leader rotation, and pipeline parallelism. Architec

Software Engineer at Wavefront (Distributed Metrics & Observability Platform)

February 1, 2017 - October 1, 2018

High-scale time-series analytics and observability platform processing millions of data points per second with sub-second query latency for high-cardinality metrics and real-time anomaly detection. Designed proxy-based ingestion using Java with secure TLS push model, buffering, and disk spillover for lossless data collection. Built distributed time-series storage engine (TSDB) supporting high-cardinality metrics and real-time querying at scale. Implemented T-Digest-based histograms enabling accurate percentile computation (p95/p99) for latency analytics. Optimized query engine (WQL) with alignment functions and streaming aggregation algorithms for cross-metric correlation. Developed AI-driven anomaly detection (AI Genie) using dynamic baselines and time-series forecasting models. Built observability pipelines powering dashboards, alerts, and real-time analytics across distributed systems.

Software Engineer at Carnegie Mellon University (Teaching Assistant)

January 1, 2016 - December 1, 2016

Teaching assistant (Computer Science) and coursework support.