AI Algorithm Engineer (Agent Direction)AI 算法工程师（Agent 方向）

About us

Bitget is the world's largest Universal Exchange (UEX), serving over 125 million users and offering access to over 2M crypto tokens, 100+ tokenized stocks, ETFs, commodities, FX, and precious metals such as gold. The ecosystem is committed to helping users trade smarter with its AI agent, which co-pilots trade execution.

Bitget is driving crypto adoption through strategic partnerships with LALIGA and MotoGP™. Aligned with its global impact strategy, Bitget has joined hands with UNICEF to support blockchain education for 1.1 million people by 2027. Bitget currently leads in the tokenized TradFi market, providing the industry's lowest fees and highest liquidity across 150 regions worldwide.

What you'll do

Business Scenario Implementation and Empowerment: Apply Agent technology to core business scenarios such as intelligent marketing, content creation, and data analysis. Through continuous algorithmic iteration, be responsible for online business indicators (such as conversion rate, efficiency improvement ratio).

Enterprise Knowledge Base and RAG System Construction: Participate in the construction of the enterprise knowledge brain, iterate the RAG full-chain optimization, document parsing, knowledge segmentation, Embedding and vector retrieval, Rerank, Query understanding and rewriting, and be responsible for the accuracy and recall rate of knowledge questions.

Agent Core Engine Development: Be responsible for the construction and iteration of the core capabilities of AI Agent, including task planning (Planning), tool invocation (Function Calling / MCP), memory management, multi-round conversation and reflection correction and other key modules' algorithm design and optimization.

Evaluation System and Frontier Exploration: Establish a scientific Agent and RAG evaluation system, drive the iterative closed-loop of model and link improvement through Bad Case analysis; keep up with the frontiers of academia and industry, quickly validate and introduce new technologies.

Project Promotion and Collaboration: Work closely with product managers and engineers to promote the engineering implementation and large-scale application of Agent solutions.

What you'll need

Computer science, artificial intelligence, mathematics and related fields, a master's degree or above is preferred. Strong foundation in machine learning and programming is required.

More than 3 years of experience in NLP, multimodal or large model-related algorithms, capable of independently leading core algorithm modules and even taking the lead in the implementation of complex AI projects from scratch.

Familiar with the Transformer architecture, with in-depth application experience of mainstream large models (such as GPT, Claude, Qwen series), possessing practical capabilities in Prompt Engineering, Finetune (SFT/DPO), model quantization and deployment. Proficient in using PyTorch, with excellent engineering skills.

In-depth understanding of the core principles of Agents (such as ReAct), with practical experience in Function Calling / MCP, familiar with mainstream frameworks like LangChain, LlamaIndex, AutoGen.

Familiar with RAG full-chain technology, with experience in using vector databases (such as Milvus, Pinecone) and tuning and optimizing retrieval engines (such as Elasticsearch).

Clear logic, excellent communication and cross-team collaboration skills, capable of making technical selection and architecture design at the direction level, and clearly communicating to different background partners to promote consensus and project progress.

Strong sense of responsibility and excellent business understanding, able to actively identify problems, propose technical solutions to drive business growth, and be responsible for the final results. Good at withstanding pressure, able to maintain stable output in the face of rapid business changes and high uncertainty.

Bonus Points

Agent Application Expert: Complete implementation experience of Agents in real scenarios such as intelligent customer service, marketing creation, data analysis, with a deep understanding of link design and effect evaluation; familiar with multi-Agent collaboration, workflow orchestration, or having experience in handling enterprise-level Agent scenarios such as high concurrency and complex permissions.

Enterprise Knowledge Base Expert: Led enterprise-level knowledge bases or knowledge middlewares projects, with in-depth practice in complex document parsing (PDF/tables), mixed retrieval, knowledge graph (GraphRAG); have experience in knowledge question answering implementation in high accuracy requirements in fields such as finance and law.

Growth/Marketing Algorithm Expert: With algorithm background in advertising computing, recommendation systems or user growth, familiar with CTR/CVR estimation, intelligent bidding, A/B testing system; have experience in intelligent generation of marketing content (copywriting/materials) or the implementation of marketing Agents.

Multimodal Generation Expert: With implementation experience of text-to-image/video, familiar with the principles of models like Stable Diffusion / Sora, proficient in customized technologies such as LoRA / ControlNet and workflow like ComfyUI.

岗位职责：

业务场景落地与赋能：将 Agent 技术应用于核心业务场景，通过算法持续迭代，对线上业务指标（如转化率、提效比率）负责。

企业知识库与RAG体系建设：参与建设企业知识大脑，迭代 RAG 全链路优化，文档解析、知识切分、Embedding 与向量检索、Rerank、Query 理解与改写，对知识问答的准确率和召回率负责。

Agent 核心引擎研发：负责 AI Agent 的核心能力建设与迭代，包括任务规划（Planning）、工具调用（Function Calling / MCP）、记忆管理、多轮对话与反思纠错等关键模块的算法设计与优化。

评测体系与前沿探索：建立科学的 Agent 与 RAG 评测体系，通过 Bad Case 分析驱动模型和链路的迭代闭环; 紧跟学术界和工业界前沿，快速验证并引入新技术。

项目推动与协作：与产品经理、工程师紧密合作，推动 Agent 解决方案的工程化落地与规模化应用。

任职要求：

计算机、人工智能、数学等相关专业，硕士及以上学历优先，具备扎实的机器学习与编程基础。

3年以上 NLP、多模态或大模型相关算法经验，具备独立负责核心算法模块、乃至主导复杂AI项目从0到1落地的能力。

熟悉 Transformer 架构，对主流大模型（如 GPT、Claude、Qwen 系列）有深入应用经验，具备 Prompt Engineering、Finetune (SFT/DPO)、模型量化与部署的实战能力。熟练使用 PyTorch，工程能力过硬。

深入理解 Agent 核心原理（如 ReAct），有 Function Calling /MCP 的实战经验，熟悉 LangChain、LlamaIndex、AutoGen 等主流框架。

熟悉 RAG 全链路技术，有向量数据库（如 Milvus, Pinecone）与检索引擎（如 Elasticsearch）的使用和调优经验。

逻辑清晰，具备优秀的沟通和跨团队协作能力，能进行方向级技术选型与架构设计，并清晰地传达给不同背景的合作方，推动共识与项目进展。

具备强烈的责任心和出色的业务理解力，能主动发现问题，提出技术解决方案驱动业务增长，对最终结果负责。抗压能力好，能在业务快速变化和高度不确定的环境中保持稳定产出。

加分项

Agent 应用专家：有 Agent 在智能客服、营销创作、数据分析等真实场景的完整落地经验，对链路设计、效果评估有深刻理解; 熟悉多 Agent 协同、工作流编排，或有处理高并发、复杂权限等企业级 Agent 场景的经验。

企业知识库专家：主导过企业级知识库或知识中台项目，在复杂文档解析（PDF/表格）、混合检索、知识图谱（GraphRAG）方面有深入实践; 在高准确率要求的金融、法务等领域有知识问答落地经验。

增长/营销算法专家：具备计算广告、推荐系统或用户增长的算法背景，熟悉 CTR/CVR 预估、智能出价、A/B 实验体系; 有营销内容（文案/素材）智能生成或营销 Agent 的落地经验。

多模态生成专家：有文生图/视频的落地经验，熟悉 Stable Diffusion / Sora 类模型原理，并精通 LoRA / ControlNet 等定制化技术和 ComfyUI 等工作流。

Why Bitget?

• Bitget is the world's leading web 3 platform for copy trading and one of the world's largest and most respected exchanges
• We are a global company with staff members from over 50 different countries and regions
• We are growing and looking for world-class ambitious talents to help us continue this journey
• We have a streamlined structure that empowers employees to work efficiently, delivering the best results in a short timeframe
• We offer competitive salaries and benefits
• Blockchain technology and digital assets have the potential to change finance in a way no other technology can - be part of it!

If you are ambitious and believe that digital assets could be the next financial and technological revolution, please apply!

For more information regarding candidates' personal data processing, please refer to Bitget Candidate Privacy Notice.