Software / AI Native Engineer

Role: Software / AI Native Engineer

Location: St. louis, MO/ Arlington, VA/ NYC, NY

Type: Contract

Day-to-Day Job Duties

• Design, develop, and productionize AI agents, LLM integrations, and agentic workflows supporting enterprise applications and developer-productivity use cases.
• Build modern, cloud-native applications and engineering solutions on AWS, integrating AI capabilities into enterprise-grade software platforms.
• Use GitHub Copilot and/or Claude Code CLI as part of the daily software-development workflow to accelerate coding, testing, debugging, refactoring, and solution delivery.
• Design and develop microservices, APIs, cloud-native applications, and distributed software components following enterprise software-engineering practices.
• Develop production-ready integrations using AWS Bedrock, OpenAI, Anthropic APIs, Azure AI Foundry, or equivalent enterprise AI platforms, where applicable.
• Build and integrate AI-agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Strands, and Bedrock Agents.
• Build Model Context Protocol (MCP) servers and MCP-enabled integrations to connect AI agents with enterprise systems, tools, data, and services.
• Develop enterprise Retrieval-Augmented Generation (RAG) solutions, with focus not only on retrieval but also retrieval quality, grounding, evaluation, and production reliability.
• Build internal developer platforms and engineering-productivity capabilities that allow software teams to incorporate AI-assisted development into their engineering lifecycle.
• Implement LLM observability and evaluation frameworks using platforms such as Langfuse, LangSmith, Braintrust, Weights & Biases, or equivalent technologies.
• Incorporate AI governance and responsible-AI controls, including guardrails, prompt-injection defense, audit logging, access controls, and appropriate operational monitoring.
• Develop proofs of concept and MVPs rapidly and mature successful prototypes into scalable, supportable production solutions.
• Work across the full engineering lifecycle including architecture, development, unit testing, automated testing, CI/CD, deployment, monitoring, troubleshooting, and production support.
• Remain actively hands-on with software development and contribute production code as an individual contributor, rather than operating solely in an architecture or management capacity.
• Collaborate with product owners, architects, engineering teams, security, cloud/platform teams, and business stakeholders to convert AI opportunities into implementable production solutions.

Basic Qualifications:

• Minimum 8+ years of overall software engineering experience, with demonstrated experience building enterprise-grade software solutions.
• Minimum 5+ years of hands-on experience in modern software engineering, including microservices, REST APIs, cloud-native architecture, DevOps, and CI/CD.
• Minimum 3+ years of strong hands-on AWS experience, developing or operating enterprise applications and services in AWS environments.
• Minimum 2+ years of hands-on experience building AI/ML, Generative AI, LLM-integrated, or agentic applications, including at least one solution deployed into a production environment.
• Demonstrated hands-on experience with GitHub Copilot and/or Claude Code CLI as part of the candidate's regular coding workflow, with the ability to provide specific examples of how AI-assisted development has been used.
• Demonstrated experience personally building an AI agent, LLM integration, or agentic workflow that reached production, rather than only developing demonstrations or proofs of concept.
• Strong hands-on software-engineering capability in at least one modern programming language such as Python, Java, JavaScript/TypeScript, or equivalent.
• Strong understanding of enterprise software-engineering principles including APIs, distributed systems, application security, automated testing, version control, observability, CI/CD, and production support.
• Demonstrated experience developing and deploying applications using cloud-native engineering practices.
• Must be a currently active hands-on engineer, with individual-contributor coding experience within approximately the last six months.
• Strong problem-solving skills and the ability to move from business or engineering requirements through design, coding, deployment, and production support.

Nice to Have:

• 2+ years of experience with modern GenAI/agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Strands, or AWS Bedrock Agents.
• Hands-on experience building an MCP server or MCP-enabled integration. This should be considered a highly differentiating capability.
• Production experience with AWS Bedrock, OpenAI APIs, Anthropic APIs, Azure AI Foundry, or equivalent enterprise AI platforms.
• Experience building internal developer platforms or engineering-productivity products.
• Experience implementing RAG systems in production, including retrieval-quality measurement and evaluation rather than only vector-database implementation.
• Experience with LLM observability and evaluation technologies such as Langfuse, LangSmith, Braintrust, or Weights & Biases.
• Experience implementing enterprise AI governance / Responsible AI frameworks, including model/agent guardrails, prompt-injection defenses, audit logging, monitoring, and security controls.