Staff AI Engineer
亚斯集团 (TAG) 是美国最大和最可靠的零售医疗保健业务支持组织之一，已支持超过20,000名医疗保健专家和团队成员，在48个州内拥有近1,500个健康与福祉办事处。该团队以独立实践主人和临床医生合作为一体：证明医疗服务可以更好更智能化。TAG 提供了综合的集中商业支持服务，推动五大面向消费者企业的影响：作为我们持续投资人工智能驱动的创新的一部分，我们正在寻找一名工作人员 AI 工程师加入我们的不断增长的 AI 团队。这是一个实践上发挥作用的角色，为医疗企业提供创新的解决方案。理想候选人将带来现代人工智能系统，多代理系统和框架，LLM 基础架构和软件工程方面的深入专业知识。主要责任：· 设计和开发企业规模的多代理系统，利用使用 Google ADK,Agentspace,MCP,RAG 和 A2A 管弦乐器的 LLMs 和自主代理框架。· 设计并实现使用 BigQuery 和 Vertex AI Engine 来建立知识和事实精确的响应。·优化对管弦乐队，知识基础，多步骤推理和决策的代理。· 进行分布式培训工作流程，在线推断系统以及低延迟服务架构，以谷歌云原生服务为实际性能优化的建筑。· 通过 Vertex AI 和现代云原生技术设计可扩展，安全，符合和生产级的 AI 织物和 AI 代理工作流程。· 创建可重复使用的 agent 编排层，可观测以及治理框架，以加速 TAG 品牌中 Agentic AI 的采用。· 与跨功能利益相关者合作将业务要求转化为技术规格。·拥有从数据收集和实施到部署和监控的所有人工智能开发生命周期。
查看英文原文
The Aspen Group (TAG) is one of the largest and most trusted retail healthcare business support organizations in the U.S. and has supported over 20,000 healthcare professionals and team members with close to 1,500 health and wellness offices across 48 states in four distinct categories: dental care, urgent care, medical aesthetics, and animal health. Working in partnership with independent practice owners and clinicians, the team is united by a single purpose: to prove that healthcare can be better and smarter for everyone. TAG provides a comprehensive suite of centralized business support services that power the impact of five consumer-facing businesses: Aspen Dental, ClearChoice Dental Implant Centers, WellNow Urgent Care, Chapter Aesthetic Studio, and Lovet. Each brand has access to a deep community of experts, tools and resources to grow their practices, and an unwavering commitment to delivering high-quality consumer healthcare experiences at scale.
Job Description:
As part of our continued investment in AI-driven innovation, we are looking for aStaff AI Engineerto join our growing AI team. This is a hands-on role delivering innovative solutions for the healthcare enterprise. The ideal candidate will bring deep expertise in modern AI systems, multi-agent systems & frameworks, LLM-based architecture, and software engineering.
Key Responsibilities:
- Architect and develop enterprise-scale multi-agent systems leveraging LLMs and autonomous agent frameworks using Google ADK, Agentspace, MCP, RAG, and A2A orchestration.
- Design and implement RAG pipelines using BigQuery and Vertex AI Engine for knowledge grounding and factually accurate responses.
- Optimize agents for orchestration, knowledge grounding, multi-step reasoning, and decision-making.
- Design and implement distributed training workflows, online inference systems, and low latency serving architectures optimized for real-world performance, using Google cloud-native services.
- Engineer scalable, secure, compliant and production-grade AI fabric and AI agent workflows using Vertex AI and modern cloud-native technologies.
- Create reusable agent orchestration layers, observability hooks, and governance frameworks that accelerate Agentic AI adoption across TAG brands.
- Partner with cross-functional stakeholders in translating business requirements into technical specifications.
- Own the full AI development lifecycle – from data collection and implementation to deployment and monitoring.
- Implement intelligent observability and automation strategies to ensure AI system reliability and performance at scale.
Qualifications & Experience:
- BS in Computer Science, or related technology field or equivalent experience.
- 2+ years of experience in Agentic AI engineering.
- 4+ years of experience in AI/ML engineering
- 8+ years of experience in software engineering, or platform engineering
- Proven track record of building and deploying production-grade AI/ML systems at scale.
- Deep understanding of modern AI model architectures (e.g., transformers, diffusion models) and system design.
- Strong hands-on expertise with Vertex AI (including model training, pipelines, orchestration, deployment, and monitoring) and Google’s Agentic AI stack.
- Hands-on with one or more of these agent orchestration frameworks: Google ADK/Agentspace,LangChain, LangGraph, LlamaIndex, CrewAI or AutoGen.
- Proficiency in Python, LLM integration workflows, MCP (Model Context Protocol) for tool integration and A2A (Agent-to-Agent) orchestration for multi-agent workflows.
- Expertise in distributed training, online inference, and low latency serving architectures.
- Experience with Kubernetes, Cloud Run, and Dataflow/PubSub for scalable deployment.
Preferred Qualifications:
- Experience with AI governance frameworks and responsible AI practices (Vertex AI Model Monitoring, BigQuery logging, Looker dashboards).
- Contributions to open-source AI projects or publications in leading AI/ML conferences.
- Experience with multi-modal models and advanced optimization strategies & frameworks.
- Experience automating, architecting and governing production grade MLOps infrastructure to scale, optimize, and observe AI workloads.
Annual Salary Range: $170,000-$200,000/year, with a generous benefits package that includes paid time off, health, dental, vision, and 401(k) savings plan with match.
If you are an applicant residing in California, please view our privacy policy here:
View CA Privacy Policy
Originally posted on Himalayas