Lead Agentic Software Engineer

About

Why choose between doing meaningful work and having a fulfilling life? At MITRE, you can have both. MITRE people are committed to tackling our nation's toughest challenges—and we’re committed to the long‑term well‑being of our employees. MITRE is a not‑for‑profit corporation chartered to work for the public interest, with no commercial conflicts to influence what we do. Our R&D centers create lasting impact in fields such as cybersecurity, healthcare, aviation, defense, and enterprise transformation. We offer competitive benefits, exceptional professional development opportunities, and a culture of innovation that embraces adaptability, collaboration, technical excellence, and people in partnership.

Department Summary

Do you want to engineer software systems that contribute to solving our nation’s most critical problems? Work alongside engineers, scientists, and domain specialists who are experts in their fields. Apply your skills and experience to solve tangible, high‑impact challenges for government sponsors while benefiting from meaningful learning and growth opportunities. We invest in your development so you can build a long‑term career here.

Roles & Responsibilities

• Design, develop, test, and deploy mission software and data platforms using agentic/AI‑assisted workflows with clear human accountability and review.
• Stand up and operate agentic development toolchains (code/test/review agents, copilots, automation bots) integrated into standard engineering practices.
• Rapidly prototype mission capabilities with agentic methods and mature them into production‑grade systems (security, reliability, scalability, observability).
• Define, implement, and enforce guardrails for agentic engineering (approved tools/models, data handling, secrets, provenance, auditability, safe prompting).
• Establish evaluation and quality gates for AI‑generated artifacts (tests, static/security analysis, coding standards, CI checks, acceptance criteria).
• Architect, build, and operate distributed cloud systems (AWS/multi‑cloud) using agentic techniques to manage performance, resilience, cost, and troubleshooting.
• Design and integrate APIs, backend services, and data flows; build and operate data pipelines and orchestration where applicable.
• Automate DevSecOps and CI/CD with AI‑aware controls (supply‑chain security, dependency/container/IaC scanning, SAST/DAST, policy‑as‑code) and repeatable releases.
• Produce and maintain documentation, runbooks, and compliance‑ready evidence for AI‑assisted engineering, including observability integrations (e.g., Splunk).
• Lead enablement: mentor teams, advise stakeholders/customers on agentic adoption, develop best practices/playbooks, and drive measurable process improvement.

Basic Qualifications

• Minimum of 8 years of related experience with a Bachelor’s degree; or 6 years with a Master’s degree; or a PhD with 3 years’ experience; or equivalent combination of education and work experience.
• U.S. citizen eligible to obtain and maintain a Secret clearance.
• Entrepreneurial, innovative, and collaborative spirit with curiosity to explore and push software development boundaries.
• Strong software engineering fundamentals and Python proficiency, including secure coding, code review, automated testing, and maintainable design patterns.
• Hands‑on experience using agentic/AI‑assisted development tools (e.g., Copilot, code agents, test generation, PR review automation) and integrating them into the Software Development Life Cycle.
• Experience designing guardrails for AI‑enabled engineering (tool/model selection, prompt/context hygiene, secrets handling, provenance, auditability, policy/compliance constraints).
• Experience establishing quality/evaluation practices for AI‑generated outputs (automated checks, unit/integration tests, static/security analysis, human‑in‑the‑loop review standards).
• Leadership/enablement skills: mentoring, setting engineering standards, and advising stakeholders/customers on responsible adoption and change management.
• Minimum of 50 % hybrid on‑site work.

Preferred Qualifications

• Advanced degree in a technical discipline (Software Engineering, Computer Science, Computer Engineering, Mathematics, etc.).
• Active Top Secret clearance preferred.
• Proven experience building, deploying, and operating LLM/agent systems (e.g., RAG, tool/function calling, orchestration frameworks) in production, including constrained/classified environments.
• Strong AI/agent security background, including threat modeling/red‑teaming and implementing safety controls (prompt injection defenses, data loss/exfiltration prevention, least‑privilege tool execution, sandboxing/content filtering).
• Mature evaluation and quality practices for LLMs/agents (golden sets, regression benchmarking, judge models; hallucination/jailbreak resistance and task success metrics).
• Platform engineering/DevSecOps expertise: CI/CD delivery platforms, artifact management, and software supply‑chain/provenance controls (SBOMs, signing/attestation/SLSA, policy‑as‑code).
• Cloud‑native operations depth across Kubernetes and IaC/multi‑cloud, with strong observability (tracing/logs/agent telemetry, audit logging/Splunk) and MLOps/model serving (hosting, gatewaying, rate/cost controls, monitoring).
• Experience supporting mission/operational systems and external integrations (mission partners/vendors), including regulated environments (NIST 800‑53/RMF, FedRAMP, DoD ILs) and producing audit‑ready evidence/artifacts.

Compensation

• Salary range: $156,800 – $196,000 – $235,200 annually (midpoint).

Work Location

• Hybrid (minimum 50 % on‑site).