AI代理开发工程师 | 远程拉美地区仅限
AI Agent Developer | Remote LATAM Only
我们寻找一位高度专业的AI代理开发人员，以构建先进的AI驱动解决方案，通过尖端技术赋能企业。
该职位专注于设计、开发和优化利用机器学习、自然语言处理（NLP）和自动化框架的AI驱动代理。
您将与跨职能团队合作，交付能够提升业务运营、客户互动和自动化流程的智能解决方案。
该职位为100%远程工作，但仅对拉丁美洲（LATAM）地区的候选人开放。此地区以外的申请将不被考虑。
关键职责
- 为客户服务、流程自动化和知识检索设计和开发AI驱动代理。
- 实现大型语言模型（LLMs）和NLP技术以提升AI代理能力。
- 优化提示工程和检索增强生成（RAG）技术以提高效率和准确性。
- 将AI模型与API、云服务和现有企业系统集成。
- 微调AI模型并持续提升其上下文感知能力和解决问题的能力。
- 使用向量数据库、嵌入和知识图谱实现AI记忆和推理。
- 与数据科学家、软件工程师和产品经理等跨职能团队合作，部署AI驱动的解决方案。
- 通过A/B测试、反馈循环和真实用户交互监控和提升AI性能。
要求
所需技能与经验
- 精通AI/ML框架：TensorFlow、PyTorch、LangChain、OpenAI API、Hugging Face 或类似工具。
- 在NLP、LLM微调和嵌入模型方面有丰富经验。
- 有检索增强生成（RAG）和提示工程的实际经验。
- 精通Python、FastAPI、Flask 或类似后端框架。
- 有向量数据库（Pinecone、Weaviate、FAISS、ChromaDB 等）的经验。
- 熟悉云服务（AWS、Azure 或 GCP）和无服务器架构。
- 有将AI与API驱动的应用程序和自动化流程集成的经验。
- 熟悉CI/CD流水线、版本控制（Git）和敏捷方法论。
- 具备强大的问题解决和分析能力，热爱AI创新。
优先条件
- 有多代理架构和AI驱动决策系统的经验。
- 理解图神经网络（GNNs）和符号AI。
- 有LLM编排经验
查看英文原文
We are looking for a highly skilled AI Agent Developer to build advanced AI-driven solutions that empower businesses through cutting-edge technologies.
This role focuses on designing, developing, and optimizing AI-powered agents that leverage machine learning, natural language processing (NLP), and automation frameworks.
You will collaborate with cross-functional teams to deliver intelligent solutions that enhance business operations, customer interactions, and automation workflows.
This role is 100% remote but only open to candidates based in Latin America (LATAM). Applications outside this region will not be considered.
Key Responsibilities
- Design and develop AI-driven agents for customer service, process automation, and knowledge retrieval.
- Implement LLMs (Large Language Models) and NLP techniques to improve AI agent capabilities.
- Optimize prompt engineering and retrieval-augmented generation (RAG) techniques for efficiency and accuracy.
- Integrate AI models with APIs, cloud services, and existing enterprise systems.
- Fine-tune AI models and continuously improve their context awareness and problem-solving capabilities.
- Work with vector databases, embeddings, and knowledge graphs for AI memory and reasoning.
- Collaborate with cross-functional teams, including data scientists, software engineers, and product managers, to deploy AI-driven solutions.
- Monitor and improve AI performance using A/B testing, feedback loops, and real-world user interactions.
Requirements
Required Skills & Experience
- Proficiency in AI/ML frameworks: TensorFlow, PyTorch, LangChain, OpenAI API, Hugging Face, or similar.
- Strong experience in NLP, LLM fine-tuning, and embedding models.
- Hands-on experience with retrieval-augmented generation (RAG) and prompt engineering.
- Expertise in Python, FastAPI, Flask, or similar backend frameworks.
- Experience with vector databases (Pinecone, Weaviate, FAISS, ChromaDB, etc.).
- Knowledge of cloud services (AWS, Azure, or GCP) and serverless architectures.
- Experience integrating AI with API-driven applications and automation workflows.
- Familiarity with CI/CD pipelines, version control (Git), and Agile methodologies.
- Strong problem-solving and analytical skills, with a passion for AI innovation.
Preferred Qualifications
- Experience with multi-agent architectures and AI-driven decision-making systems.
- Understanding of graph neural networks (GNNs) and symbolic AI.
- Experience with LLM orchestration tools such as AutoGPT, BabyAGI, CrewAI, or OpenDevin.
- Contributions to open-source AI projects or publications in AI/ML research.
- Knowledge of ethical AI principles and responsible AI deployment.
Originally posted on Himalayas