GenAI Engineer Agentic AI & Cloud Engineering

Title:
GenAI Engineer – Agentic AI & Cloud Engineering
Location :
Rockville, MD or McLean, VA
Target Start Date : ASAP
Type: contract
Pay Rate: DOE

We are seeking a hands-on GenAI Engineer to help design, build, and product ionize enterprise AI solutions focused on agentic systems, LLM-powered workflows, and intelligent automation platforms. This role is centered on building scalable AI tools and frameworks that transform proof-of-concepts into production-ready applications across the organization.

The ideal candidate combines strong software engineering fundamentals with deep hands-on experience building AI agents, RAG pipelines, MCP integrations, and cloud-native GenAI applications. This is an engineering-first role for someone who actively codes, architects solutions, and thrives in fast-moving AI environments.

This position contributes throughout the software development lifecycle, from architecture and prototyping through deployment, optimization, and operational support.

• Design and build LLM-powered agent systems using frameworks such as:
  • Lang Chain
  • Lang Graph
  • AWS Strands Agents SDK
  • or equivalent agent orchestration platforms
• Develop and product ionize:
  • AI assistants
  • autonomous and semi-autonomous agents
  • intelligent workflow automation tools
  • MCP-integrated systems
  • RAG-based enterprise search and retrieval solutions
• Build agent harness architectures that combine:
  • LLM reasoning
  • deterministic execution
  • tool orchestration
  • structured output validation
  • guardrails and fallback handling
• Implement:
  • agent memory and context management
  • tool routing and orchestration
  • API integrations
  • vector search and retrieval workflows
  • secure execution tracing and auditing
• Partner with teams to take POCs and experimental AI concepts into production-scale initiatives
• Help drive internal adoption of AI tooling and identify opportunities to expand GenAI capabilities across engineering teams

• Build scalable AI applications and services on AWS cloud infrastructure
• Develop backend services and APIs supporting agent workflows and AI tooling
• Engineer cloud-native AI solutions leveraging:
  • AWS Bedrock
  • Lambda
  • Step Functions
  • S3
  • EMR
  • EKS/ECS
  • API Gateway
• Contribute to CI/CD pipelines, infrastructure automation, observability, and deployment processes
• Ensure secure handling of enterprise and sensitive data within AI systems and workflows

• Build and optimize retrieval pipelines supporting GenAI applications and RAG architectures
• Develop SQL and Python-based processing for large-scale datasets and retrieval workflows
• Work with high-volume cloud data environments and distributed processing systems
• Support structured and unstructured data ingestion for AI-powered applications

• Hands-on experience building:
  • AI agents
  • agentic workflows
  • LLM-powered applications
  • RAG pipelines
• Strong understanding of:
  • prompt engineering
  • memory architectures
  • context management
  • tool usage and orchestration
  • verification and guardrail patterns
• Experience integrating with foundation models such as:
  • Anthropic Claude
  • OpenAI models
  • Amazon Nova
  • or equivalent LLM platforms
• Experience communicating with and integrating:
  • MCP servers
  • APIs
  • external tools
  • enterprise data sources

• Strong hands-on coding ability in:
  • Python (primary)
  • SQL
• Ability to write:
  • modular
  • maintainable
  • production-quality code
• Experience with:
  • REST APIs
  • backend engineering
  • automation frameworks
  • test automation
  • CI/CD pipelines

• Strong AWS experience including:
  • Bedrock
  • Lambda
  • S3
  • EMR
  • Step Functions
  • Cloud Watch
  • EKS/ECS
• Experience with:
  • Docker
  • Kubernetes
  • Infrastructure as Code
  • Git Lab CI / Jenkins / Git Hub Actions

• Experience using AI-assisted engineering tools such as:
  • Amazon Q Developer
  • Git Hub Copilot
  • Claude
  • ChatGPT
• Familiarity with AI-assisted software development workflows and rapid prototyping approaches

• Deeply hands-on with GenAI engineering
• Comfortable building systems from concept through production deployment
• Strong technical depth with the ability to rapidly experiment and iterate
• Able to bridge AI concepts,…