AI Native Engineer

Job Title: Senior Technology Consultant – AI Native Engineer

Location: Location: Arlington, VA, New York, NY;  Hybrid work model

Local candidates preferred. 

Overall Experience: 7+ Years

Role Summary
We are seeking a hands-on Senior AI Native Engineer to design, build, and deliver production-grade AI agents, LLM-integrated applications, and developer productivity tooling on AWS.
The ideal candidate is an experienced software engineer who remains actively involved in coding and uses GitHub Copilot and/or Claude Code CLI as part of their day-to-day development workflow. This role requires proven experience taking agentic AI or LLM-based solutions beyond proof-of-concept into production environments, with strong foundations in cloud-native engineering, Microservices, APIs, and DevOps.

Day to Day Job Duties
Design, develop, and deploy production-grade AI agents and agentic workflows.
Build LLM-powered applications and integrate AI capabilities into enterprise systems and engineering workflows.
Develop cloud-native services and AI solutions using AWS and AWS-native technologies.
Build and maintain Microservices, REST APIs, event-driven services, and enterprise integrations.
Use GitHub Copilot and/or Claude Code CLI as part of daily software development and engineering activities.
Design and implement agent workflows using frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Strands, or Bedrock Agents.
Build integrations using Model Context Protocol (MCP) and develop MCP servers where applicable.
Develop internal developer platforms, engineering productivity tools, and reusable AI capabilities.
Design and implement production-grade RAG solutions, including retrieval, relevance evaluation, and quality optimization.
Integrate enterprise applications with AWS Bedrock, OpenAI, Anthropic, or other LLM APIs.
Implement LLM observability, tracing, evaluation, and performance monitoring.
Develop AI guardrails, audit logging, security controls, and prompt-injection defenses.
Build automated testing and evaluation processes for AI/LLM applications.
Implement CI/CD pipelines and support production deployment, monitoring, troubleshooting, and continuous improvement.
Participate in architecture discussions and code reviews while remaining a strong hands-on individual contributor.

Basic Qualifications – Must Have
7+ years of experience in hands-on software engineering, including Microservices, APIs, cloud-native applications, and enterprise software development.
3+ years of strong hands-on experience with AWS, DevOps/CI-CD, and cloud-native architecture.
Proven hands-on experience personally building and deploying an AI agent, LLM integration, or agentic workflow into a production environment.
Current hands-on development experience, with active individual-contributor coding experience within the last 6 months.
Demonstrated day-to-day use of GitHub Copilot and/or Claude Code CLI for software development, with the ability to explain specific real-world use cases.

Technical Skills
Agentic AI: AI Agents, Agentic Workflows, Tool Calling, Multi-Agent Systems
Agent Frameworks: LangGraph, LangChain, CrewAI, AutoGen, Strands, Bedrock Agents
Protocols: Model Context Protocol (MCP)
AI/LLM Platforms: AWS Bedrock, Anthropic APIs, OpenAI APIs, Azure AI Foundry
Cloud: AWS
Architecture: Microservices, REST APIs, Event-Driven Architecture, Cloud-Native Applications
AI Coding Tools: GitHub Copilot, Claude Code CLI
DevOps: Git, CI/CD, automated testing and deployment
LLM Observability: Langfuse, LangSmith, Braintrust, Weights & Biases
AI Patterns: RAG, Embeddings, Vector Search, LLM Evaluation, Guardrails

Strongly Preferred
Hands-on experience developing an MCP server or MCP-enabled enterprise integration.
Production experience with LangGraph, LangChain, CrewAI, AutoGen, Strands, or Bedrock Agents.
Strong production experience with AWS Bedrock.
Experience building internal developer platforms or engineering productivity products.
Experience implementing production RAG systems with measurable retrieval quality and evaluation frameworks.
Experience implementing LLM observability and evaluation using Langfuse, LangSmith, Braintrust, or W&B.
Experience with AI governance and Responsible AI controls, including guardrails, prompt-injection protection, access controls, and audit logging.
Experience designing secure enterprise integrations between AI agents and internal systems.
Strong software architecture, troubleshooting, communication, and problem-solving skills.