Staff AI Engineer - Enterprise LLM & Multi-Agent Systems

TAG - The Aspen Group

United States

Remote

USD 170,000 - 200,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Paid time off

Health insurance

Dental insurance

Vision insurance

401(k) with match

Job summary

The Aspen Group (TAG) is accelerating AI-driven innovation across its healthcare network. We seek a Staff AI Engineer to design and implement enterprise-scale, multi-agent AI systems, leveraging LLMs and advanced orchestration frameworks.

You will own end-to-end development from data collection to deployment and monitoring, ensuring scalable, secure and compliant AI solutions for our brands. You will partner with cross-functional teams, drive architecture choices, and push the boundaries of AI

Qualifications

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).
Strong hands-on expertise with Vertex AI (model training, pipelines, orchestration, deployment, monitoring) and Google’s Agentic AI stack.
Hands-on with agent orchestration frameworks: Google ADK/Agentspace, LangChain, LangGraph, LlamaIndex, CrewAI or AutoGen.
Proficiency in Python, LLM integration workflows, MCP for tool integration and A2A 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.

Responsibilities

Architect and develop enterprise-scale multi-agent systems with LLMs and autonomous agent frameworks.
Design and implement RAG pipelines using BigQuery and Vertex AI Engine for knowledge grounding.
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.
Engineer scalable, secure, compliant and production-grade AI fabric and agent workflows using Vertex AI and cloud-native tech.
Create reusable agent orchestration layers, observability hooks, and governance frameworks across TAG brands.
Partner with cross-functional stakeholders to translate business requirements into technical specs.
Own the full AI development lifecycle – data collection, implementation, deployment and monitoring.
Implement observability and automation strategies to ensure AI system reliability at scale.