Senior AI Agent Engineer

Ethereum Technologies LLC; Charlotte (NC); Remote; USD 83,000 - 110,000; Full time

Job summary

Ethereum Technologies in Charlotte, NC (Remote) is seeking a Senior AI Agent Engineer to design, implement, and harden production-grade AI agents. You will develop end-to-end agent lifecycles, integrate with MCP, temporal workflows, and CI/CD pipelines, and collaborate with security and infrastructure teams to ensure governance and reliability.

The role requires deep experience with Python/Java, AI governance, and agent orchestration, along with hands-on work in data storage, knowledge graphs,

Qualifications

• 7+ years in software engineering for enterprise-grade solutions.
• 1–2+ years building LLM-based apps, AI agents, or agentic workflows.
• 3+ years producing software with Python and/or Java.
• 1+ year with MCP, tool calling, and agent frameworks.

Responsibilities

• Design, develop, and harden production-grade AI agents across end-to-end lifecycle.
• Build and orchestrate Finder, Planner, and Executor agents for remediation and deployment.
• Develop agent orchestration and tool integrations using MCP and Temporal.
• Integrate agents with enterprise tools and CI/CD pipelines.
• Ensure governance, audit trails, and security controls throughout agent design.
• Collaborate with cross-functional teams to integrate into existing workflows.

Skills

LLM-based apps

Python/Java

AI governance

Security controls

Context engineering

Agent orchestration

Root-cause analysis

Tools

MCP

Temporal

GitLab CI/CD

JFrog Artifactory

Neo4j/Cypher

Kafka

MongoDB/SQL

Job description

US Citizen, Green Card, H-1B, OPT-EAD, CPT, Other

Job Title: Senior AI Agent Engineer
Location: Charlotte, NC(Remote)
Duration: 24 Months + Extension
Bill Rate: $69/hour (C2C)
Job Type: W-2, 1099, C2C
Client: To Be Discussed Later
Work Authorization: US Citizen, Green Card, OPT-EAD, CPT, H-1B, H4-EAD, Other

Job Description:

Design, develop, and harden production-grade AI agents across the end-to-end detect → store → plan → remediate → deploy lifecycle.
Build and orchestrate Finder, Planner, and Executor agents to identify issues, prioritize remediation, execute approved actions, validate changes, and support controlled deployments.
Develop agent orchestration and tool integrations using Model Context Protocol (MCP), tool calling, agent frameworks, and workflow engines such as Temporal.
Develop and integrate agents with the Actionable Observation store, Overwatch state machine and prioritization capabilities, and operator console.
Integrate agents with GitLab pipelines, GitLab CI/CD, JFrog Artifactory, canary deployment workflows, and Tenable Vulnerability Management (UVM) as a vulnerability-finding source.
Expose and consume enterprise knowledge graphs containing data lineage and environment context through MCP, ensuring agents have governed, read-only access to relevant information.
Implement event processing, data storage, and state management using Kafka, MongoDB, SQL, and SQLite.
Develop and query knowledge graphs using Neo4j and Cypher to support contextual retrieval, dependency analysis, and remediation planning.
Implement automated code-change workflows, AI-assisted code generation, test generation, and lockdown-test practices to validate remediation changes before deployment.
Apply context engineering and specification-driven development to improve agent accuracy, consistency, traceability, and maintainability.
Embed human-approval gates, audit trails, access controls, and AI governance controls throughout agent design, execution, and deployment.
Ensure autonomous workflows comply with enterprise security standards, change-management processes, deployment controls, and production-readiness requirements.
Support vulnerability remediation and software version-currency initiatives using CVE, EPSS, CVSS, End-of-Life (EOL), and End-of-Support (EOS) considerations.
Implement controlled deployment patterns, including canary releases and incremental rollouts, to reduce operational risk.
Troubleshoot agent execution failures, integration issues, workflow exceptions, and deployment problems; perform root-cause analysis and implement corrective actions.
Monitor and improve agent reliability, performance, scalability, and observability using Dynatrace or comparable tools where applicable.
Collaborate with application development, infrastructure, cybersecurity, DevSecOps, architecture, and production support teams to integrate agents into existing workflows.
Document reusable agent patterns, technical designs, integration approaches, governance controls, onboarding procedures, and operational best practices.
Coach application, infrastructure, and security teams on agent onboarding, secure usage, human oversight, and adoption of the autonomous operating model.
Participate in technical design reviews, code reviews, automated testing, release planning, and continuous improvement initiatives.
Own AI agent solutions across requirements, design, development, integration, testing, deployment, monitoring, and ongoing enhancement.

Basic Qualifications:

Minimum 7+ years of experience in software engineering or production application development, delivering and supporting enterprise-grade solutions.
Minimum 1–2+ years of hands‑on experience developing LLM‑based applications, Generative AI solutions, AI agents, or agentic workflows.
Minimum 3+ years of hands‑on experience developing production software using Python and/or Java.
Minimum 3+ years of experience with Git, GitLab CI/CD, automated testing, and software delivery practices.
Minimum 1+ year of hands‑on experience with AI agent orchestration, MCP, tool calling, and agent frameworks or equivalent technologies.
Minimum 1+ year of experience with agent development platforms such as AWS Agent Core, Kiro, or equivalent technologies.
Minimum 1+ year of experience with workflow orchestration engines such as Temporal or equivalent platforms.
Minimum 2+ years of experience developing automated code-change workflows, code validation, automated test generation, or lockdown-test practices.
Minimum 1+ year of practical experience applying context engineering and specification‑driven development to AI or software engineering workflows.
Minimum 2+ years of experience working with event‑processing or data‑storage technologies such as Kafka, MongoDB, SQL, or SQLite.
Minimum 1+ year of experience with Neo4j, Cypher, graph databases, or knowledge‑graph querying.
Minimum 3+ years of experience integrating applications with CI/CD pipelines, artifact repositories, deployment platforms, or enterprise tools.
Minimum 2+ years of experience implementing secure software engineering practices, access controls, audit trails, or human‑in‑the‑loop approval mechanisms.
Minimum 1+ year of experience implementing AI governance, security guardrails, or operational controls for AI‑driven automation.
Minimum 3+ years of experience with SDLC, automated testing, change management, release processes, and production support.
Minimum 3+ years of experience troubleshooting complex application or integration issues, conducting root‑cause analysis, and implementing corrective actions.
Minimum 2+ years of experience collaborating with cross‑functional teams, including application development, infrastructure, DevOps, or cybersecurity.
Minimum 1+ year of experience documenting technical designs, reusable engineering patterns, operational procedures, or implementation standards.
Minimum 1+ year of experience providing technical guidance, mentoring engineers, or coaching teams on engineering practices or new technology adoption.
Demonstrated ability to explain personal technical contributions, agent architecture, implementation decisions, challenges, and business outcomes from previous projects

We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.