Agentic AI Engineer (Dallas)

We are seeking a highly skilled Agentic AI Engineer to design, develop, and deploy autonomous AI agents and workflows within the AWS ecosystem. The ideal candidate will have hands-on expertise in building multi-agent AI systems, integrating LLMs (such as Gemini, GPT, or Claude), and orchestrating intelligent pipelines that leverage cloud services for scalability, observability, and security.

This role requires a deep understanding of AI architecture, vector search, orchestration frameworks, and event-driven cloud systems. You will collaborate with data engineers, MLOps teams, and solution architects to deliver real-world AI capabilities that adapt, reason, and act autonomously.

Key Responsibilities

Agentic AI & LLM Integration

• Design and implement autonomous AI agents capable of reasoning, planning, and executing workflows using LLMs (Gemini, GPT, Claude, etc.).
• Implement multi-agent coordination frameworks (e.g., LangChain, CrewAI, AutoGen, or Semantic Kernel).
• Build adaptive memory systems and contextual knowledge retrieval pipelines using Bedrock and Vector Search.
• Integrate with external APIs and enterprise systems using secure, event-driven architectures.
  
  

AWS Cloud Engineering

• Develop and deploy AI workloads in AWS leveraging:
• Bedrock, Pub/Sub, Cloud Run, Cloud Functions, and BigQuery.
• ECS for storage and Cloud Composer (Airflow) for orchestration.
• Build containerized microservices (Docker / Kubernetes / GKE) for scalable AI workflows.
• Implement CI/CD pipelines using Cloud Build or GitHub Actions for rapid iteration.
  
  

Data & Intelligence Layer

• Architect retrieval-augmented generation (RAG) pipelines using GCP Vector Search, Pinecone, or Weaviate.
• Connect unstructured and structured data sources to LLMs using Bedrock.
• Design prompt optimization, context management, and long-term memory storage strategies.
  
  

Security, Governance, and Observability

• Enforce IAM, service accounts, and least-privilege policies across agent workflows.
• Integrate Cloud Logging, Cloud Monitoring, and Dynatrace (if applicable) for full observability of agent actions.
• Implement data governance and compliance standards for AI model usage and external API calls.
  
  

Innovation & Collaboration

• Partner with product, ML, and software teams to define use cases for agentic automation.
• Continuously evaluate emerging frameworks for multi-agent systems and adaptive reasoning.
• Contribute to architectural roadmaps, PoCs, and AI innovation initiatives within the organization.
  
  

Qualifications

• Bachelors or Masters degree in Computer Science, Data Science, or related field.
• 5 years of experience in cloud-based development (GCP preferred).
• 3 years of experience with LLM-based applications (LangChain, LlamaIndex, or OpenAI APIs).
• Strong programming skills in Python, Go, or Node.js.
• Experience with RAG, vector databases, and agent orchestration frameworks.
• Familiarity with Vertex AI, GKE, Pub/Sub, BigQuery, and Cloud Functions.
• Solid understanding of MLOps, microservices, and event-driven design.
  
  

Preferred Skills

• Experience with Google Gemini API or other advanced foundation models.
• Knowledge of Autonomous AI frameworks (e.g., AutoGPT, BabyAGI, CrewAI).
• Exposure to LangGraph or Semantic Kernel for graph-based agent design.
• Experience integrating AI observability tools (Weights & Biases, Arize AI, or Vertex AI Model Monitoring).
• Understanding of RAG governance, compliance, and cost optimization strategies.