Architect - R01571180

Team: Digital Engineering : Digital Engineering

Location: New York, New York, United States

Commitment: Employee

Workplace Type: remote

Primary Skills

• AWS Networking, AWS Kenesis, AWS Elastic Cache, AWS PaaS Services, AWS EKS, AWS Cognito, Solution Architecture - AWS, AWS Redshift

Job requirements

• Job Title: AI / Agentic AI Architect
  Role: Architect – Agentic AI Platforms & Applications
  Location: NY
• Work Type: Remote with occasional travel
 
• Job Summary
  We are looking for an experienced AI / Agentic AI Architect to design, build, and scale enterprise-grade AI agents, autonomous workflows, and LLM-powered applications. The role combines hands-on AI engineering, solution architecture, cloud-native modernization, and stakeholder advisory to move high-value AI use cases from rapid experimentation to secure, governed, production-ready deployment.
 
• Key Responsibilities
  • Define agentic AI reference architectures across LLM applications, RAG pipelines, tool/function calling, memory systems, multi-agent orchestration, and enterprise integrations.
  • Design and deploy AI agents and autonomous workflows for business functions such as Finance, Legal, Operations, Sales, Support, and Growth.
  • Evaluate foundation models and enterprise AI platforms including Gemini, Vertex AI, OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, and open-source LLMs.
  • Integrate AI solutions with enterprise platforms such as Google Workspace, Slack, CRM systems, internal APIs, databases, and knowledge repositories.
  • Implement observability, evaluation, guardrails, monitoring, reliability controls, and responsible AI practices for production applications.
 
• Required Skills & Experience
  • 8+ years of software engineering, solution architecture, enterprise architecture, or platform engineering experience.
  • 2+ years of hands-on experience building AI, GenAI, LLM-powered, or agentic applications; production deployment experience preferred.
  • Strong understanding of LLMs, RAG, prompt engineering, vector databases, tool/function calling, context management, memory systems, and AI workflow orchestration.
  • Hands-on experience with frameworks such as LangChain, LangGraph, CrewAI, Google ADK, AutoGen, Semantic Kernel, or similar.
  • Strong engineering skills in Python and one or more of Java, Go, Node.js, React, TypeScript, APIs, microservices, SQL/NoSQL, and event-driven systems.
  • Experience with Google Cloud, AWS, or Azure, including Docker, Kubernetes, CI/CD, DevSecOps, and cloud-native deployment patterns.
•  
•  
• Nice to Have Skills
  • Experience with AI evaluation frameworks, observability tools, guardrails, and feedback loops.
  • Knowledge of fine-tuning, model optimization, open-source LLM deployment, multi-agent coordination, and autonomous decision-making systems.
  • Experience with Pinecone, Weaviate, Chroma, Vertex AI Vector Search, Google Workspace APIs, Slack integrations, or enterprise automation tools.
  • Exposure to AI-driven SDLC tools, cloud certifications, open-source AI contributions, or fast-paced innovation environments.
  Impact & Value
  • Enable clients to move from AI experimentation to secure, scalable, production-grade agentic AI solutions.
  • Accelerate enterprise automation, developer productivity, operational efficiency, and time-to-market through reusable AI frameworks and modern engineering practices.
  • Drive measurable business value through AI-first platforms aligned to customer success, care, entrepreneurial ownership, and engineering excellence.