返回信息流招聘software engineer若干
https://apply.careers.microsoft.com/careers/job/1970393556658222?domain=microsoft.com&hl=en，
Software Engineer - Agent Infrastructure & LLM Platform
Microsoft AI Asia Platform Team
Level: 61-64 (SDE II - Senior SDE)
Location: Beijing / Suzhou
About the Team
Microsoft AI Asia Platform Team builds the foundational infrastructure powering Microsoft's AI products across Azure, Copilot, Bing, and internal engineering systems. We develop enterprise-grade Agent Runtime, large-scale model training/serving frameworks, and next-generation AI developer toolchains. Our infrastructure directly impacts how millions of developers build and deploy AI applications globally.
Role Overview
We are seeking a software engineer with strong multi-language programming capabilities to build high-performance, reliable infrastructure for Agent systems. You will work on the core runtime for autonomous agents, distributed LLM serving, and RL-based training pipelines—turning cutting-edge AI research into production-grade platform services.
Key Responsibilities
o Agent Runtime Development: Design and implement high-throughput runtime systems supporting Tool Use, Function Calling, and multi-agent orchestration at scale
o LLM Serving Infrastructure: Optimize inference stacks including request scheduling, KV cache management, continuous batching, speculative decoding, and model parallelism
o AI Developer Tooling: Develop AI-assisted development tools and applications (similar to Claude Code, OpenClaw) to boost engineering / work productivity
o Platform Abstraction: Transform experimental agent capabilities into reusable platform APIs, SDKs, and managed services for upstream product teams
Basic Qualifications
o Bachelor's degree or higher in Computer Science, Engineering, or related technical field
o Strong multi-language programming and vibe-coding proficiency: Production-level experience with Rust, C++, C#, and Python (expertise in at least two required, familiarity with all four preferred)
o Systems engineering fundamentals: Deep understanding of concurrency, memory management, performance optimization, and distributed systems architecture
o Agent architecture knowledge: Solid grasp of modern agent paradigms (ReAct, CoT, Function Calling, Agent State Management) with hands-on implementation experience
o LLM infrastructure foundation: Understanding of Transformer inference mechanics, experience with serving frameworks (vLLM, TensorRT-LLM, Triton, or custom stacks)
Preferred Qualifications
o RL Training Experience: Hands-on experience with RLHF, DPO, PPO, or offline RL for language model alignment;
o High-Performance Deployment: Expertise in model quantization (GPTQ/AWQ/GGUF), compiler optimization (MLIR/TVM), or heterogeneous hardware acceleration (GPU/TPU/NPU)
o Agent Systems Depth: Contributions to open-source agent frameworks (LangGraph, AutoGen, OpenHands, CodeR) or deep technical analysis of Claude Code/ OpenClaw implementations
o Cloud-Native Engineering: Experience building services on Kubernetes, service mesh architectures, or Azure/GCP/AWS platforms at scale
Core Tech Stack
Rust · C++ · C# · Python · Agent Runtime · LLM Serving · Kubernetes
What We Offer
o Direct impact on Azure-scale AI infrastructure serving millions of users
o Early-stage involvement in incubating technologies similar to GitHub Copilot and internal AI coding agents
o Access to large-scale GPU clusters (H100/A100) and cutting-edge model weights
o Cross-functional collaboration with Microsoft Research and global product teams
o Clear engineering career progression with mentorship from senior architects
To Apply: Please include links to GitHub repos, technical blogs, or specific examples demonstrating your experience with Agent systems, LLM infrastructure, or multi-language systems programming.
这是一条镜像帖。来源：北邮人论坛 / job-info / #978672同步于 2026/3/7
JobInfo机器人发帖
微软 社招 Agent Infrastructure & LLM Platform base北京 苏
abaisa
2026/3/7镜像同步0 回复
订阅后，新回复会通过你的通知中心匿名送达。
0 条回复
暂无回复 · 你可以订阅本帖等待新回复。