Senior AI Architect

Job Title: Senior AI SDLC Engineer
Location: McLean, VA (5 Days Onsite)
Job Summary
We are seeking a forward-thinking AI-Driven SDLC Engineer to transform software development from linear automation workflows into an agentic, multi-agent execution model using frameworks like Kiro, Claude Code, or GitHub Copilot.
The ideal candidate will design and implement specialized AI agents that collaborate across the Software Development Life Cycle (SDLC) to produce production-grade, enterprise-ready software. These agents will handle responsibilities such as intent analysis, architecture design, implementation, testing, debugging, and security validation, while maintaining clear context boundaries and execution efficiency.
You will help drive an engineering paradigm where structured intent and design artifacts guide AI execution, ensuring traceability, governance, and quality across all stages of delivery.
Responsibilities
Agent Architecture & Creation: Design task-specific agents (Code Reviewer, API Designer, Test Generator, Security Validator) with clearly defined responsibilities, context boundaries, and input/output contracts.
Orchestration & Workflow Automation: Build multi-agent workflows that handle initialization, task delegation, sequencing, parallelization, and cleanup — replacing linear pipelines with collaborative, event-driven execution models.
AI-Driven SDLC Integration: Embed agentic workflows across the full delivery lifecycle — from requirements and architecture through implementation, testing, code review, and release — with seamless context and artifact handoffs between stages.
Context & Memory Management: Maintain agent reliability through context isolation, structured memory, and efficient handling of complex or long-running tasks to prevent context overload.
Tooling & Enterprise Integration: Connect AI workflows to source control, work management, CI/CD, and service management systems for end-to-end traceability from intent to production.
Automated Quality Engineering: Generate unit, integration, and behavioral tests alongside validation logic — shifting quality left to improve coverage, defect detection, and release confidence.
Performance & Continuous Improvement: Monitor workflows using quality signals, cycle time, and defect trends — continuously refining to reduce manual effort, boost productivity, and accelerate releases.
Governance, Safety & Compliance: Apply guardrails for output validation, security checks, and safe AI execution to ensure all generated artifacts meet enterprise standards and regulatory requirements.
Required Qualifications
Agentic SDLC & AI Engineering
Proven experience designing and implementing AI-driven agentic workflows, with strong understanding of multi-agent systems, context management, and spec-driven development.
Software Engineering Background
Solid foundation in backend or full-stack development, API design, and system integration — with working knowledge of version control, CI/CD pipelines, and cloud-native architecture.
LLM & Prompt Engineering
Hands-on experience embedding LLMs into engineering workflows — defining task-specific prompts, controlling AI behavior through structured inputs, and ensuring consistent, reliable outputs.
Systems Design & Decomposition
Ability to break complex systems into modular, parallelizable components with clearly defined agent boundaries and execution units.
AI Safety & Reliability
Familiarity with AI safety practices including output validation, hallucination mitigation, and adversarial testing strategies.
Data & Context Engineering
Experience with context retrieval mechanisms (RAG patterns), structured knowledge sources, and memory management strategies for AI systems.