AI Architect - Generative AI, LLMs & AWS
Location: West Palm Beach, FL (Remote)
Fulltime
Role Summary
We are looking for a hands-on AI Architect to lead the design, development, enhancement, and deployment of an enterprise AI platform powered by Large Language Models (LLMs). The ideal candidate will combine strong software engineering skills with deep expertise in Generative AI, Agentic AI, and AWS cloud services to build scalable, secure, and production-ready AI applications.
This role requires active involvement in solution architecture, coding, cloud deployment, performance optimization, and mentoring engineering teams.
Key Responsibilities
- Design, develop, and enhance an enterprise AI platform integrating multiple Large Language Models (LLMs).
- Architect and implement scalable AI solutions using modern Agentic AI frameworks and Retrieval-Augmented Generation (RAG) architectures.
- Build intelligent AI agents capable of reasoning, planning, tool execution, and workflow orchestration.
- Develop secure, scalable, and highly available cloud-native AI applications on AWS.
- Design and implement REST APIs and microservices to expose AI capabilities to enterprise applications.
- Integrate AI services with enterprise systems, databases, APIs, and third-party platforms.
- Deploy, monitor, and optimize AI workloads on AWS ensuring performance, scalability, security, and cost efficiency.
- Work closely with product owners and engineering teams to translate business requirements into technical solutions.
- Drive architecture reviews, code quality, CI/CD automation, and engineering best practices.
- Evaluate emerging LLMs, AI frameworks, and cloud services to continuously improve the AI platform.
- Mentor developers and provide technical leadership across AI initiatives.
Required Technical Skills
Generative AI
- Strong hands-on experience with OpenAI GPT, Anthropic Claude, Llama, Mistral, Amazon Nova, or similar foundation models.
- Experience building enterprise-grade LLM applications.
- Expertise in Retrieval-Augmented Generation (RAG).
- Prompt engineering, prompt optimization, embeddings, semantic search, and model evaluation.
- Experience integrating multiple LLM providers and managing model orchestration.
Agentic AI
Hands-on experience with one or more of:
- LangChain
- LangGraph
- CrewAI
- Microsoft Semantic Kernel
- AutoGen
- Amazon Bedrock Agents
Experience developing:
- Multi-agent workflows
- Tool calling
- Function calling
- Memory management
- Planning and reasoning agents
AWS Cloud
Strong hands-on experience with:
- Amazon Bedrock
- Amazon SageMaker
- AWS Lambda
- ECS/EKS
- API Gateway
- Step Functions
- Amazon S3
- DynamoDB
- Amazon OpenSearch
- Amazon Aurora
- CloudWatch
- IAM
- VPC
- EventBridge
- Secrets Manager
Experience with Infrastructure as Code (Terraform, AWS CDK, or CloudFormation) is highly desirable.
Programming
- Python (mandatory)
- FastAPI / Flask
- REST APIs
- Microservices
- Docker
- Kubernetes
- Git
- CI/CD pipelines
Databases & Search
Experience with:
- PostgreSQL
- DynamoDB
- OpenSearch
- Pinecone
- Weaviate
- Chroma
- FAISS
- Milvus
Preferred Qualifications
- Experience building AI products from concept to production.
- Strong understanding of LLMOps, MLOps, observability, and AI monitoring.
- Experience implementing AI guardrails, responsible AI, and enterprise security controls.
- Familiarity with event-driven and serverless architectures.
- Knowledge of authentication, authorization, and API security.