Research Engineer focused on optimizing LLM/VLM inference systems, including inference engines, serving frameworks, and deployment pipelines. Requires expertise in performance optimization techniques, C/C++, Python, ML frameworks, and production-scale LLM inference deployment.

Research Engineer focused on optimizing LLM/VLM inference systems, including engines, serving frameworks, and deployment pipelines, using advanced performance techniques and collaborating with research teams.

Seeking an experienced Research Scientist/Engineer to design and build next-generation AI infrastructure at ByteDance, focusing on large-scale systems, AI, and emerging hardware to enable efficient and scalable AI workloads. The role involves architecting the end-to-end AI factory, exploring emerging trends, optimizing ML stack performance, and aligning cross-functional teams.

Develop and optimize large-scale distributed ML training and inference systems, focusing on LLM inference frameworks and GPU/CUDA performance optimization for high-performance LLM inference engines.

Research Scientist/Engineer role focused on defining and building next-generation AI infrastructure for large-scale AI workloads, including training, RL, and inference, considering compute, storage, networking, chips, power, and data layers. The role involves tracking AI trends, optimizing system performance, and aligning cross-functional teams.

Research Engineer/Scientist focused on designing and implementing a high-performance KV cache layer for LLM inference to improve latency, throughput, and cost-efficiency. This role involves optimizing intermediate state storage and retrieval for transformer-based LLMs, collaborating with inference and serving teams, and potentially extending open-source KV stores or building custom GPU-aware caching layers.

Develop and optimize high-precision, low-latency hand tracking algorithms for XR scenarios, including monocular/multiple vision and multi-sensor fusion. Build 3D gesture pose estimation models for challenging conditions, optimize real-time inference performance on mobile XR headsets, and lead the development of a multimodal ML interaction framework for natural XR interaction. Promote patent layout and publish papers in top conferences.

Senior Research Engineer/Scientist focused on designing and implementing a high-performance KV cache layer for LLM inference to improve latency, throughput, and cost-efficiency. This role involves optimizing caching for transformer-based models, collaborating with inference teams, and potentially extending open-source KV stores or building custom GPU-aware caching layers.

Research Engineer/Scientist focused on designing and implementing a high-performance KV cache layer for LLM inference to improve latency, throughput, and cost-efficiency in transformer-based model serving.

Research Engineer/Scientist focused on applying AI/ML to database management systems, including query optimization, indexing, workload forecasting, and developing self-managing databases. The role involves integrating AI models into production systems and publishing research findings.

Research Engineer/Scientist role focusing on applying AI/ML to database management systems, including query optimization, indexing, workload forecasting, and developing self-managing databases. The role involves research and development, integrating AI models into production systems, analyzing large datasets, and publishing findings. Requires a PhD and strong publication record in AI/databases/systems, with experience in database internals and ML frameworks.

Research Engineer/Scientist focused on applying AI/ML to database management systems, including query optimization, indexing, and workload forecasting, with a goal of building AI-native data infrastructure and intelligent optimization. The role involves research and development, integrating models into production, and publishing findings.

Machine Learning Engineer focused on designing, implementing, and optimizing distributed inference infrastructure for large-scale AI models in the consumer domain, specifically for ads, feeds, and search ranking.

Machine Learning Platform Engineer to develop and maintain a platform supporting deep learning models for code development, testing, training, model deployment, and other core business functions. The platform is foundational for recommendation, advertising, and search systems, involving recommended systems and distributed training of large-scale deep learning models.

Machine Learning Engineer focused on optimizing resource efficiency in distributed orchestration and scheduling for training and inference systems, particularly for large-scale recommendation models. The role involves building and optimizing training system architectures and online inference architectures, integrating with MLops processes, and working within Kubernetes/Godel ecosystems.

Software Engineer focused on optimizing and deploying ML models for edge NPUs in VR/AR devices, involving quantization, performance profiling, and hardware-aware optimizations to meet latency, memory, and power constraints.

Software Engineer specializing in ML compilers for edge NPU architectures, focusing on optimizing latency, memory, power, and thermal constraints for ML inference on target hardware. Requires strong compiler and deep learning model understanding, with preferred experience in quantization and ML compiler stacks.

Develop transaction-level models of edge NPU architectures for ML workloads (CNNs, Transformers) to simulate execution, analyze performance, and optimize for latency, memory, and power targets. Requires strong C/C++ and System C proficiency, computer architecture understanding, and experience with ML accelerator modeling.

The Tech Lead Software Engineer will design and build large-scale, container-based cluster management and orchestration systems with extreme performance, scalability, and resilience, focusing on GPU and AI accelerator infrastructure for LLM inference. This role involves architecting next-generation cloud-native systems, collaborating on inference solutions using various LLM engines, and contributing to open-source projects.

Tech Lead Software Engineer focused on building and maintaining large-scale, Kubernetes-native LLM inference infrastructure (AIBrix). The role involves designing and architecting GPU-optimized orchestration systems for hyper-scale environments, collaborating on inference solutions using various LLM engines, and staying current with AI/ML infrastructure advancements.

Research Scientist focused on DPU and AI infrastructure, aiming to accelerate distributed training and inference by co-designing software and hardware solutions. Explores AI/ML infrastructure acceleration leveraging DPUs, GPUs, and custom hardware.

Research Scientist role focused on designing and developing DPU network software for AI/ML workloads, optimizing distributed training and inference, and exploring software-hardware co-design for cloud and AI computing infrastructure.

Research Scientist role focused on designing and developing DPU network software for AI/ML workloads, including distributed training and inference acceleration, and software-hardware co-design.

Tech Lead, Research Scientist focused on DPU and AI infrastructure, optimizing distributed training and inference by leveraging DPUs, GPUs, and custom hardware. The role involves designing and developing high-performance network software, collaborating on software-hardware co-design, and driving end-to-end performance optimization.

This role focuses on designing and developing DPU network software and exploring AI/ML infrastructure acceleration using DPUs, GPUs, and custom hardware to optimize distributed training and inference. It involves software-hardware co-design and end-to-end performance optimization for cloud-scale computing.

Senior Cloud Acceleration Engineer focused on DPU and AI infrastructure, involving software-hardware co-design to optimize distributed training and inference performance. Requires strong C/C++ and Linux systems development, with experience in networking, distributed systems, or AI/ML systems.

Senior Software Engineer to design and build large-scale, container-based cluster management and orchestration systems for LLM inference, focusing on performance, scalability, and cost-efficiency. The role involves architecting GPU and AI accelerator infrastructure, collaborating on inference solutions using various LLM engines, and staying current with AI/ML infrastructure advancements.

Software Engineer focused on building and maintaining large-scale, Kubernetes-native AI compute infrastructure for LLM inference, emphasizing performance, scalability, and cost-efficiency. The role involves architecting GPU-optimized systems and collaborating on inference solutions using various LLM engines.

Software Engineer focused on building and maintaining large-scale, Kubernetes-native LLM inference infrastructure (AIBrix) with a focus on performance, scalability, and cost-efficiency. The role involves architecting GPU-optimized systems, collaborating on inference solutions using various LLM engines, and contributing to open-source projects.

This role focuses on designing and developing DPU network software and exploring AI/ML infrastructure acceleration, specifically for distributed training and inference. It involves software-hardware co-design and performance optimization of systems related to AI computing.

ByteDance is seeking a Cloud Acceleration Engineer to focus on DPU and AI infrastructure. The role involves designing and developing high-performance DPU network software, collaborating on software-hardware co-design, and exploring AI/ML infrastructure acceleration for distributed training and inference. The position requires strong C/C++ and Linux systems development skills, with a background in areas like software-hardware co-design, distributed systems, networking, or AI/ML systems.

Tech Lead for an Applied Machine Learning (AML) team focused on building and advancing distributed orchestration platforms for recommendation systems, ads ranking, and search ranking. The role involves leading a team of ML Engineers, setting technical strategy for resource efficiency, distributed training, and online inference systems, and optimizing large-scale distributed orchestration and scheduling strategies.

Machine Learning Platform Engineer to develop and maintain a platform supporting deep learning models for code development, testing, training, model deployment, and other core business functions. The role supports recommendation, advertising, and search systems, focusing on distributed training of large-scale deep learning models.

Software Engineer role focused on building and optimizing large-scale compute infrastructure (Kubernetes, Serverless) to support AI and LLM workloads, including training and inference. The role involves enhancing cluster management, developing intelligent scheduling systems leveraging AI models for resource optimization, and leading infrastructure for next-gen ML workloads.

Senior Software Engineer focused on building and optimizing large-scale compute infrastructure (Kubernetes, Serverless) for AI and LLM workloads, including scheduling, resource management, and inference. The role involves developing intelligent scheduling systems using AI models and contributing to open-source projects.

Senior Software Engineer focused on building and optimizing large-scale compute infrastructure (Kubernetes, Serverless) for AI and LLM workloads, including scheduling, resource management, and inference. The role involves enhancing performance, scalability, and cost-efficiency for training and inference, with a focus on heterogeneous resources (CPU, GPU) and open-sourcing key technologies.

Software Engineer role focused on building and optimizing large-scale compute infrastructure (Kubernetes, Serverless) for AI and LLM workloads, emphasizing resource efficiency, scheduling, and reliability. The role involves developing intelligent scheduling systems leveraging AI models and leading infrastructure for ML training/inference.

Machine Learning Engineer focused on optimizing and deploying AI algorithms on Qualcomm chips for XR devices, emphasizing low-power consumption and performance improvement. This role involves close collaboration with hardware vendors and contributing to the AI toolchain and technical ecosystem.

Site Reliability Engineer for an Applied Machine Learning team focused on next-generation recommendation algorithms and platforms. The role involves ensuring high availability and creating automated systems for large-scale AI/recommendation systems.

Develops and optimizes high-speed network infrastructure and communication frameworks specifically for AI/LLM applications, focusing on performance, scalability, and reliability in large-scale data centers.