Req 26-03433
AI Agent Engineer
$95,000–$100,000/yr
- Requisition. 26-03433
- Location. Reston, VA
- Type. Onsite · Direct Hire
- Compensation. $95,000–$100,000/yr
- Posted. Oct 15, 2026
Your résumé routes to the recruiter who owns this requisition. Identity-verified profile, never resold or syndicated.
About the role
About Client
Client is an information technology and business process outsourcing company. It provides a range of IT services and solutions to clients worldwide, including application development and maintenance, digital transformation, cloud services, automation and artificial intelligence, enterprise solutions, and quality assurance and testing.
The company serves various industries such as banking and financial services, insurance, healthcare and life sciences, manufacturing, retail, consumer packaged goods, and travel and transportation.It has a strong focus on emerging technologies and digital innovation. It leverages technologies like robotic process automation (RPA), machine learning, natural language processing, and blockchain to help its clients enhance operational efficiency, improve customer experience, and drive business growth.
Salary Range: $95K-$100K/Annum
Job Description
- We are seeking a senior/lead-level engineer with deep hands-on experience in AI coding agents, developer productivity platforms, agent administration, security, and cloud infrastructure.
- This resource will help lead the implementation, administration, functional validation, security validation, and operational management of enterprise coding-agent capabilities.
- The individual should be capable of working independently, troubleshooting complex integrations, establishing technical standards, and providing technical leadership to engineering teams adopting coding agents.
- The ideal candidate should have experience operating AI coding technologies in enterprise production environments, rather than solely developing proofs of concept.
Core Qualifications
- AI Coding Agents and Developer AI Platforms
- Deep hands-on experience with OpenAI Codex / coding agents and GitHub Copilot, including implementation, configuration, administration, troubleshooting, and enterprise deployment.
- Experience configuring and administering capabilities such as:
- Organization and enterprise-level policies
- User and group access
- Repository access
- Agent permissions
- Model configuration
- Tool access
- Policy enforcement
- Usage controls
- Enterprise security controls
- Experience implementing and supporting coding-agent workflows across the software development lifecycle (SDLC).
- Ability to assess coding-agent behavior from both a functional and administrative/platform perspective.
- Agent Engineering
- Strong hands-on experience designing, configuring, and building AI agents, including:
- Agent configuration and orchestration
- Custom coding agents
- GPTs / custom assistants
- Agent tools and tool integrations
- Plugins, Skills, or equivalent extensibility mechanisms
- Prompt and instruction architecture
- Agent context management
- Tool selection and tool execution
- Multi-agent or orchestrated agent workflows
- MCP – Model Context Protocol
- Strong working knowledge of Model Context Protocol (MCP), including experience building and securing MCP servers.
- Experience should include:
- MCP scopes and permissions
- Authentication and authorization
- Fine-grained authorization
- Identity propagation
- Credential handling
- Secure access to enterprise APIs and systems
- Restricting agent access using least-privilege principles
- Experience designing security boundaries around MCP tools is highly desirable.
- Identity, Authentication, and Authorization
- Deep understanding of enterprise identity and access management, with hands-on experience implementing several of the following:
- SSO, SAML, OAuth 2.0, OpenID Connect (OIDC), Identity Providers (IdP), SCIM provisioning, AWS IAM, AWS IAM Identity Center, Microsoft Active Directory / Entra ID, Bearer tokens, JWT tokens, Service identities, Role-based access control (RBAC), Fine-grained authorization
- Candidates should understand authentication versus authorization and be capable of designing identity flows for both human users and autonomous agents.
- Experience implementing least-privilege access for AI agents is strongly preferred.
- AWS and AI Platform Experience
- Strong working knowledge of AWS, including hands-on experience with: Amazon Bedrock, Amazon Bedrock Agents, Amazon Bedrock Agent Core, IAM roles and policies, ECS, Application Load Balancer (ALB)
- Lambda, API Gateway, CloudWatch, Secrets Manager and/or Parameter Store, VPC/networking fundamentals, Programming
- Strong proficiency in Python is required.
- Candidates should be comfortable developing: REST APIs, Agent services, Automation utilities, Integration services, Test harnesses, Validation frameworks
- Experience with asynchronous Python, API development frameworks, and structured logging is preferred.
- Security and Authorization Validation
- Unauthorized repository access
- Tool authorization
- MCP permission boundaries
- Identity propagation
- Token handling
- Privilege escalation
- Least-privilege enforcement
- Secrets exposure
- Cross-user or cross-project access
- Prompt-injection/tool-abuse scenario
- Experience developing automated agent evaluation frameworks, test harnesses, or regression suites is strongly preferred.
- Preferred / Nice-to-Have Qualifications
- Shell scripting / Bash
- PowerShell
- Prompt-injection and AI security testing
Experience Profile
- Preference should be given to candidates who can demonstrate:
- Significant recent hands-on experience with GitHub Copilot or comparable enterprise AI coding platforms.
- Hands-on experience with OpenAI Codex or production coding-agent technologies.
- Multiple years of experience engineering and operating enterprise developer platforms, cloud platforms, or AI/ML platforms.
- Production experience administering developer-facing technology used by multiple engineering teams.
- Evidence of leading technically complex implementations rather than participating solely as an individual application developer.
What happens after you apply.
1. Verified profile
Submit your résumé and complete the ApTask identity + skills verification. We check right-to-work, background, and technical calibration once — never resell or re-verify — so future roles surface faster.
2. Recruiter calibration call
Within one business day, the recruiter who owns this requisition reviews your profile against the client's specific stack, arrangement, and start-date requirements. You'll hear back either way — no ghosting.
3. Client interview
If your profile is a fit, we present you to the hiring team. Most clients run 2-3 interview stages: hiring-manager screen, technical panel, and final. We prep you with the exact scorecard criteria before each round.
4. Offer + onboarding
On acceptance, you onboard W-2 with ApTask. Benefits, payroll, and timesheets run through us. Your recruiter stays your point of contact for the length of the engagement.