Build and deploy custom model context protocol (MCP) connectors for new and existing services
Design and implement custom agentic workflows using cloud AI platforms
Develop server-side application logic and APIs that integrate AI capabilities with existing enterprise systems
Contribute to the development and maintenance of reusable AI component libraries and shared code infrastructure
Write high-quality code, applying best practices, coding standards, and design patterns for AI systems
Participate in the entire AI solution lifecycle, including requirement gathering, design, development, testing, and deployment, using an agile, iterative process
Participate in code reviews and ensure code quality through effective testing strategies and security validation
Collaborate with infrastructure teams, security teams, developers, designers, testers, project managers, product managers, and project sponsors
Communicate tasking estimation and progress regularly to a development lead and product owner through appropriate tools
Ensure seamless integration with backend systems, cloud services, databases and messaging systems
Team with other developers, fostering a culture of continuous learning and professional growth in AI engineering

Requirements

At least 5+ years of professional software engineering experience with a focus on Python and TypeScript/JavaScript
Proven experience building and deploying production AI systems, custom integrations, and agentic workflows using LLM-based platforms
Hands-on experience with Model Context Protocol (MCP) architecture or similar plugin/connector frameworks and workflow orchestration tools (n8n, Airflow, LangGraph) for complex AI pipelines
Demonstrated expertise with containerization technologies (Docker, Kubernetes) and cloud-native deployment patterns for scalable AI systems
Solid understanding of Amazon Web Services cloud platform including their native AI/ML services, vector databases, graph databases, and observability solutions
Experience with RESTful API design, GraphQL, and event-driven architectures across multiple LLM providers (OpenAI, Anthropic, Bedrock, Groq)
Experience with advanced prompt engineering techniques and specialized knowledge of ensemble prompting strategies for effectively combining and synthesizing outputs from multiple LLM models
Proficient with infrastructure-as-code tools (e.g., terraform)
Experience with CI/CD pipelines and automated deployment strategies
Familiarity with security best practices for AI systems, including authentication, authorization, logging, and data encryption
Strong understanding of microservices architecture and distributed systems
Proficient with version control systems (e.g., Git) and effective collaborative development workflows
Must be a US Citizen and eligible to obtain and maintain a US Security Clearance.

Benefits

Paid Time Off
Paid Company Holidays
Medical, Dental & Vision Insurance
Optional HSA and FSA
Base and Voluntary Life Insurance
Short Term & Long-Term Disability Insurance
401k Matching
Employee Assistance Program

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

PythonTypeScriptJavaScriptModel Context Protocol (MCP)DockerKubernetesAmazon Web Services (AWS)RESTful API designGraphQLinfrastructure-as-code

Soft Skills

collaborationcommunicationtask estimationcode reviewcontinuous learningprofessional growth

Certifications

US Security Clearance