字节跳动AI Application产品与解决方案实习生-火山方舟

In this role, you will AI Solution Development: Design, develop, and deploy AI-driven applications, across domains, such as machine learning, NLP, and computer vision, addressing both business requirements and end-user needs. End to End Supply Chain Connectivity: Partner with supply chain experts to understand business goals and translate into clear technical specifications and solutions recommendation. Agent Design and Development: Design and implement intelligent agents within multi-agent systems, enabling real-time collaboration based on pre-defined goals, strategies, and data exchanges. Develop agent-based models to optimize decision-making and interactions. MCP Integration: Extend and integrate Multi-Agent Coordination Platforms(MCP) to optimize resource allocation, communication, and decision-making across multiple agents in shared environments. Data Management: Architect, design, build, and maintain data pipelines that connects across internal and external supply chain systems. Enforcing data governance and control is implemented at key matrix levels. Collaboration with Data Science Teams: Collaborate with data scientists to refine algorithms, optimize models, and enhance AI performance, focusing on model tuning, feature selection, and performance benchmarking. Testing and Validation: Conduct rigorous testing and validation of AI models, including unit testing, integration testing, and A/B testing, to ensure accuracy, reliability, and scalability before deployment. Monitoring and Maintenance: Monitor deployed AI models, track performance metrics, and implement continuous improvement strategies, including model re-training and updates based on real-world data and evolving business needs.

• In this role, you will • - AI Solution Development: Design, develop, and deploy AI-driven applications, across domains, such as machine learning, NLP, and computer vision, addressing both business requirements and end-user needs. • - Agent Design and Development: Design and implement intelligent agents within multi-agent systems, enabling real-time collaboration based on pre-defined goals, strategies, and data exchanges. Develop agent-based models to optimize decision-making and interactions. • - MCP Integration: Extend and integrate Multi-Agent Coordination Platforms(MCP) to optimize resource allocation, communication, and decision-making across multiple agents in shared environments. • - Collaboration with Data Science Teams: Collaborate with data scientists to refine algorithms, optimize models, and enhance AI performance, focusing on model tuning, feature selection, and performance benchmarking • - Testing and Validation: Conduct rigorous testing and validation of AI models, including unit testing, integration testing, and A/B testing, to ensure accuracy, reliability, and scalability before deployment. • - Monitoring and Maintenance: Monitor deployed AI models, track performance metrics, and implement continuous improvement strategies, including model re-training and updates based on real-world data and evolving business needs.

We are seeking a skilled developer to build production-grade AI applications, focusing on LLM-based agents and tool-using systems. You will integrate large language models (LLMs), retrieval-augmented generation (RAG), and external tools/APIs on GPU-accelerated stacks, enhancing agent frameworks for reliability, scalability, and safety. What You’ll Be Doing: • Design, implement, and deploy AI-powered features using LLMs, including autonomous and multi-agent workflows. • Build agent toolchains, including planning, tool/function calling, memory management, RAG integration, and enterprise API connectivity. • Enhance agent frameworks with custom planners, routers, concurrency control, state management, and retry mechanisms. • Develop evaluation and observability systems to monitor agent performance (success rates, tool-call accuracy, latency, cost, traces). • Implement safety and compliance measures, including content filtering, PII handling, and policy enforcement using guardrail frameworks. • Optimize inference pipelines for GPU performance, latency, and cost; deploy via microservices and APIs. • Manage CI/CD, containerization, and deployment; maintain monitoring, logging, and alerting; and produce clear documentation.

1. 核心算法优化：参与半导体领域核心算法优化工作，包括但不限于基于机器或深度学习进行异常检测、时序建模、图像算法等构建； 2. 算法效率与精度提升：协助团队提升算法运行效率与精度，解决实际业务中的技术难题； 3. 数据建模与分析：负责半导体相关数据的建模与分析，收集、清洗、预处理半导体生产过程数据、器件测试数据等，运用数据挖掘技术挖掘数据背后的规律与关联，为业务决策提供数据支撑； 4. 文档撰写：协助团队完成算法与模型的文档撰写工作，包括技术方案文档、实验报告、模型说明文档等，确保技术成果的可追溯性与可复用性； 5. 前沿技术跟踪：跟踪半导体领域算法与机器学习技术的前沿动态，参与技术研讨，为团队技术创新提供思路与建议。