Engineer · Researcher

Pengcheng Xu

Engineer & Researcher

Compilers · Runtimes · LLM-Agent Systems

pooytr1@gmail.com github.com/Poytr1 Shanghai, China

About

Engineer-researcher hybrid — a systems engineer and independent researcher working at the intersection of compilers, runtimes, and LLM-agent systems.

I spend my days building cloud-scale compiler, runtime, and streaming infrastructure, and my own hours researching and shipping LLM-agent tooling and developer infrastructure — turning stochastic agent behavior into the kind of deterministic, low-cost systems engineering I trust.

Tech Lead at Microsoft (Fabric Eventstreams), previously Elastic · 8+ years of cloud-scale compiler / runtime / streaming infrastructure.

Research Interests

LLM agent systems & orchestration Agentic workflows, tool-use, supervisor graphs
Inference-cost & latency optimization Making autonomous agents cheaper and faster to run
Compilers, IR/DAG & code generation For streaming and data systems
Runtime sandboxing & secure execution Multi-tenant isolation for untrusted workloads
Developer tooling & program intelligence Release intelligence, code navigation, build & delta analysis

Projects

Open-source tools and research spanning LLM-agent systems, developer tooling, and compilers.

View all projects →

Selected Work & Research

Eventstreams V3 Topology Re-architecture Microsoft Fabric · 2023–Present

As acting Tech Lead, re-architected the core real-time streaming engine onto a unified backend compilation pipeline and a high-performance IR/DAG framework. Serves Fabric customers globally at ~5M events/day with ~180% YoY growth.

Compiler / IR / DAG · codegen · distributed streaming

Sentio.xyz Agent Orchestration Open-source contributor · 348+ commits

Designed and shipped a LangGraph supervisor-graph agent orchestration system; built an LLM processor code-generation agent with multi-chain support (EVM, Sui, Aptos, Move); owned the EVM tracer, debugger, and Solidity language server.

LLM agents · supervisor graphs · multi-chain codegen

NL → Streaming-Pipeline Agent Microsoft org hackathon · 2nd place · Oct 2024

An LLM agent that compiles natural-language business constraints directly into deployable Fabric Eventstreams pipelines.

LLM agents · program synthesis · streaming

Background

Microsoft Apr 2020 – Present · Beijing → Shanghai

Technical Lead / Senior Software Engineer

Fabric Eventstreams (acting Tech Lead), Azure Stream Analytics core engine, and Azure Synapse Spark notebooks.

Elastic May 2018 – Apr 2020 · Beijing

Software Engineer

Codesearch team (joined via the Insight.io acquisition); built a high-scale Java language server on Eclipse JDT and LSP code-intelligence in Kibana.

YITU Technology Jul 2017 – Apr 2018 · Shanghai

Software Engineer Intern — Infrastructure

Infrastructure and tooling across a high-availability inference platform.

Upstream open-source microsoft/Trill tikv/tikv elastic/kibana

Education

University of Science and Technology of China

B.Sc. Computer Science & Technology

2014 – 2018 · USTC

Skills

Languages

C#PythonGo RustTypeScriptJava C++SQLScala

LLM & Agents

LLM agent designAgentic workflows Prompt/context engineering Inference-cost optimization

Systems

Distributed systemsCompiler construction LSPIR/DAG Runtime sandboxingHigh-throughput streaming

Infrastructure

Azure FabricStream Analytics SynapseOneLake ElasticsearchDocker LinuxCI/CD