代理AI工程师协作
Agentic AI Engineer Co-Op
自1869年以来，我们通过人们喜爱的食物连接了人们。我们自豪地成为令人信赖品牌的守护者。我们的产品组合包括标志性的Campbell’s品牌，以及Cape Cod、Chunky、Goldfish、Kettle Brand、Lance、Late July、Pacific Foods、Pepperidge Farm、Prego、Pace、Rao’s Homemade、Snack Factory、Snyder’s of Hanover、Swanson和V8。
在这里，你每天都能带来改变。你将获得支持，建立有成就感的职业生涯，拥有成长、创新和启发的机会。与我们一同创造历史。
Agentic AI工程师设计、构建和部署能够推理、规划、使用工具并执行多步骤工作流的自主AI系统，几乎无需人工干预。与专注于模型训练和预测的传统AI/ML工程师不同，Agentic AI工程师协调目标驱动的工作流，整合模型、工具、记忆和业务逻辑，以动态实现目标
核心职责
- 设计与开发Agentic系统：构建具备自主规划、推理和任务执行能力的智能代理，通常使用LLM（如GPT类、LLaMA）、多模态模型和自主工作流
- 协调与框架：使用LangChain、AutoGen、CrewAI、Semantic Kernel或自定义解决方案实现代理协调
- 检索增强生成（RAG）：设计并优化RAG管道以增强外部知识的推理能力，包括文档摄入、分块、嵌入、向量存储和检索排序
- 工具与记忆集成：开发能够调用API、数据库和其他工具的代理，维护记忆，并根据结果进行适应性调整
- 评估与监控：创建用于准确率、依据性、延迟和成本的评估框架；构建代理行为和故障模式的可观测性
- 模型适配：对基础模型（例如通过LoRA、适配器）进行微调或适配，以满足特定领域的需求
- 生产部署：在云原生环境中部署GenAI/Agentic系统，包括CI/CD、版本控制和运行时保护措施
- 跨职能协作：与数据科学家、ML工程师、产品团队和治理/合规相关方合作
所需技能与经验
- 2年以上AI/ML系统设计、部署或自主代理开发经验
- 编程：精通Python（有时也使用Java、C#）用于AI/ML解决方案开发
- 代理与工作流专长：具有代理协调框架和多代理系统的经验
查看英文原文
Since 1869, we've connected people through food they love. We’re proud to be stewards of amazing brands that people trust. Our portfolio includes the iconic Campbell’s brand, as well as Cape Cod, Chunky, Goldfish, Kettle Brand, Lance, Late July, Pacific Foods, Pepperidge Farm, Prego, Pace, Rao’s Homemade, Snack Factory, Snyder’s of Hanover. Swanson, and V8.
Here, you will make a difference every day. You will be supported to build a rewarding career with opportunities to grow, innovate and inspire. Make history with us.
An Agentic AI Engineer designs, builds, and deploys autonomous AI systems that can reason, plan, use tools, and execute multi-step workflows with minimal human intervention . Unlike traditional AI/ML engineers who focus on model training and prediction, agentic AI engineers orchestrate goal-driven workflows that integrate models, tools, memory, and business logic to achieve objectives dynamically
Core Responsibilities
- Design & Develop Agentic Systems: Build intelligent agents capable of autonomous planning, reasoning, and task execution, often using LLMs (e.g., GPT-class, LLaMA), multi-modal models, and autonomous workflows
- Orchestration & Frameworks: Implement agent orchestration using frameworks like LangChain, AutoGen, CrewAI, Semantic Kernel, or custom solutions
- Retrieval-Augmented Generation (RAG): Design and optimize RAG pipelines for enhanced reasoning with external knowledge, including document ingestion, chunking, embeddings, vector stores, and retrieval ranking
- Tool & Memory Integration: Develop agents that call APIs, databases, and other tools, maintain memory, and adapt based on outcomes
- Evaluation & Monitoring: Create evaluation frameworks for accuracy, grounding, latency, and cost; build observability for agent behavior and failure modes
- Model Adaptation: Fine-tune or adapt foundation models (e.g., via LoRA, adapters) for domain-specific use cases
- Production Deployment: Deploy GenAI/agentic systems in cloud-native environments with CI/CD, versioning, and runtime safeguards
- Cross-Functional Collaboration: Work with data scientists, ML engineers, product teams, and governance/compliance stakeholders
Required Skills & Experience
- 2+ years in AI/ML system design, deployment, or autonomous agent development
- Programming: Proficiency in Python (and sometimes Java, C#) for AI/ML solution development
- Agent & Workflow Expertise: Experience with agent orchestration frameworks and multi-agent communication protocols
- RAG & LLM Integration: Hands-on with RAG architectures, evaluation methodologies, and LLM integration
- Cloud & DevOps: Experience with cloud platforms (e.g., Azure, AWS) and CI/CD pipelines
- Governance & Compliance: Understanding of responsible AI, security, and compliance in regulated domains (e.g., retail)
The Company is committed to providing equal opportunity for employees and qualified applicants in all aspects of the employment relationship, including consideration for employment, without regard to race, color, sex, sexual orientation, gender identity, national origin, citizenship, marital status, protected veteran status, disability, age, religion, or any other classification protected by law.
Originally posted on Himalayas