Senior AI Researcher - Remote/Hybrid, LLM & Optimization

Home Sign Up Sign In Claude API 官方价一折起 国内直连免折腾 目前平台累计服务用户数万 企业客户超过 100 家 日均调用量稳定在百万级 能跑到这个规模 核心就一点 把基础设施做扎实 让开发者专注写代码而不是折腾网络 Promoted by aicodinginc PRO • 外包信息请发到 /go/outsourcing 节点 • 不要把相同的信息发到不同的节点 V2EX 酷工作 内推 可 relocate 悉尼 远程 Senior AI Researcher (KV Cache Optimization) rome7054 Jul views This topic created in 53 days ago, the information mentioned may be changed or developed.

团队直招 简历直达 HC 1 个 Full Time 岗位

简介

base 悉尼的一家 startup 专注于云平台的 cost deduction 如 CPU/内存的调度优化 同时也正在扩展 GPU 领域 需要懂 CUDA/KV cache/LLM optimization/调度优化的大牛

办公地点选择

• 远程 约 2-3h 时差
• relocate 到悉尼 Hybrid: 3 天办公室+2 天 WFH,可协助办理签证

Responsibilities:

• inference & Compute Optimization: Design and implement highly optimized inference pipelines and computational kernels to accelerate LLM and neural network workloads, leveraging low-level techniques such as SIMD vectorization, cache-aware memory access patterns, and hardware-specific tuning.
• Neural Network Compression & Model Optimization: Research and implement pruning, quantization, and other compression techniques to reduce model size and accelerate inference while preserving accuracy. Apply both in-training and post-training optimization methods across LLM and vision model workloads.
• Profiling & Observability: Build and utilize advanced profiling tools to identify bottlenecks across the inference and training stack-from memory bandwidth and cache utilization to CPU-side data preprocessing stalls and end-to-end pipeline throughput.
• Evaluation & Benchmarking: Design and maintain rigorous evaluation and benchmarking frameworks for systematic model comparison across optimization configurations. Develop automated pipelines (e.g., LLM-as-a-judge) to measure the impact of optimization techniques on model quality and performance.
• Mentorship: Act as a technical lead for engineers and researchers, fostering a culture of high-performance code, rigorous benchmarking, and research-to-production excellence. Drive team growth, technical interviews, and cross-functional collaboration.

Required Qualifications

• Deep Systems Expertise: 8+ years of experience in high-performance computing, AI systems, or low-level software optimization. Deep familiarity with performance-critical development including CPU/GPU architecture, memory hierarchies, SIMD/vectorization, and profiling-driven tuning.
• LLM & NN Optimization Track Record: Proven experience optimizing neural networks and LLMs through techniques such as pruning, quantization, and inference acceleration, with a demonstrated path from research to production deployment.
• Communication: Ability to translate complex systems-level constraints and optimization trade-offs into actionable research directions for modeling and engineering teams.
• Experience building evaluation frameworks, ML observability, or developer tools that help researchers understand and compare model performance across optimization configurations.
• A history of working on neural network compression, inference acceleration, or applied AI research problems that required bridging algorithmic research with high-performance implementation.
• Patent authorship or published research in AI/ML optimization.
• Experience with C/C++ inference engines, x86 intrinsics, or similar low-level performance work is a strong plus.

备注

• 以上条件不需全部满足 符合部份条件有兴趣的欢迎您来
• 年龄不限制 但是要 senior 以上的
• 不是我面试 只是内推 全英面试 需要准备好英文简历
• 因薪资范围公司 JD 没提到 可以参考 其中描述基本还是准确的 自己按照预期来提 没有上家流水检查和涨幅限制说法
• 可谈 Employee Stock Ownership Plan (ESOP) package

请邮件联系 aG95aG9AZ2xhc3N3aW5nLmNsb3VkCg

深入探索 订阅企业新闻 报名编程课程 试用高效软件 LLM 优化 系统 3 replies • 2026-07-:47:14 :00 1 deltaone Jul 10 有 Engineer 岗位吗 2 zhyd1997 Jul 10 via iPhone 有 Engineer 岗位吗 3 rome7054 OP Jul 10
需要有 CUDA/KV cache 或相关经验的 About Help Advertise Blog API FAQ Privacy Solana 5492 Online Highest 6679 Select Language 创意工作者们的社区World is powered by solitude VERSION: 3.9.8.5 36ms UTC 06:32 PVG 14:32 LAX 23:32 JFK 02:32
Do have faith in what you're doing. word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word word
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1
mmMwWLliI0fiflO&1