We are redirecting you to the source. If you are not redirected in 3 seconds, please click here.

Senior Agentic AI Software Developer at Kentro. Thank you for considering IT Concepts dba Kentro, where innovation drives opportunity and collaboration leads to success. Our dynamic community of experts is fully committed to advancing our customers' missions, fostering professional growth, and making a positive impact on our communities.                                                . By joining our supportive community, you will find that Kentro is dedicated to your personal and professional development. Together, we can drive meaningful change, spark innovation, and achieve extraordinary milestones.. Kentro is hiring a . Senior AI Agentic Software Developer. with deep experience designing, building, and deploying agent-based AI systems in regulated, security-constrained environments. This role goes beyond prompt engineering, you will architect context-aware, tool-using AI agents that operate reliably within Government Community Cloud High (GCCH) and federally compliant environments. . You will work at the intersection of LLM orchestration, contextual engineering, secure data access, and cloud-native software development, translating mission and business requirements into production-grade AI systems. . Responsibilities:. Agentic AI & Contextual Engineering . Design and implement multi-step, agentic AI workflows (planner/executor, tool-using agents, RAG + memory patterns) . Engineer robust contextual pipelines including: . Retrieval-augmented generation (RAG) . Structured memory (short-term, long-term, episodic) . Tool invocation and function calling . Control hallucination, drift, and overreach through grounding, validation, policy constraints, and ensemble methods. . Optimize context windows, token usage, and latency under federal cost, platform quotas, and performance constraints. . Secure Software Development . Build production-grade services using Python, Java, C++, Rust, GO, C#, TypeScript . Implement APIs and microservices that integrate AI agents with: . Data lake house . SharePoint . Microsoft Graph API  . Line-of-business systems . Apply secure coding practices aligned with NIST 800-53 / 800-171  . Azure GCCH and Federally Compliant Architecture.   . Design and deploy solutions in GCCH environments . Work within constraints such as: . Limited model availability . Restricted outbound network access . Controlled identity and authentication flows . Use Azure services including: . Azure AI (OpenAI / Foundry where applicable) . Azure Kubernetes Service (AKS) . Azure Functions / App Services . Azure Data Lake Storage . Azure Key Vault . Implement identity, RBAC, and managed identities aligned with federal requirements  . Compliance, Governance, and Safety . Design AI systems with auditability, traceability, and explainability . Support Authority to Operate (ATO) processes . Implement logging, monitoring, and human-in-the-loop controls . Ensure data residency, data minimization, and model usage compliance . Location: . This position can be performed remotely within the United States and will support Eastern Time working hours. Travel may be required. . 6+ years of professional software development experience . 3+ years working with LLMs, AI orchestration frameworks, or conversational AI systems . Bachelor’s or Master’s degree in one of the following: . Computer Science . Computer Engineering . Software Engineering . Data Science . Artificial Intelligence . Mathematics (with CS focus) . OR equivalent practical experience (8–10+ years) in advanced software engineering + AI systems may substitute for degree. . Hands-on experience building agentic or multi-step AI systems . Strong understanding of contextual engineering (not just prompt writing) . Experience deploying solutions in Azure Government (GCCH) or similar sovereign clouds . Technical Expertise:. Deterministic & Re-playable Agent Execution . Secure Tooling & Capability Sandboxing . Latency Engineering Under Network Constraints . Change Management for AI Behavior . Preferred Qualifications / Experience: .  . Knowledge of federal security and compliance frameworks (NIST, FedRAMP, DoD ILs) . Experience with frameworks such as: . LangChain / LangGraph . Semantic Kernel . AutoGen or equivalent agent frameworks . Familiarity with: . Vector databases (Azure AI Search, PostgreSQL + pgvector, etc.) . Evaluation frameworks for LLM outputs . Prior experience supporting federal civilian or DoD customers . Understanding of tradeoffs between local model hosting vs API-based model access . Experience with AI governance or responsible AI implementation . Building autonomous agent frameworks . Tool-using LLMs . Memory architectures (vector DBs) . Planning loops (ReAct, Tree-of-Thought, etc.) . Guardrails & policy enforcement . Secure deployment in regulated environments . Clearance Requirement:. Public Trust required; ability to obtain higher clearance eligibility preferred . U.S. Citizenship . What Success Looks Like in This Role:. AI agents behave predictably, securely, and within scope . Context is intentionally engineered, not accidentally accumulated . Systems pass security review without last-minute redesign . Stakeholders trust the AI because it is auditable and explainable . Solutions work within GCCH and federal constraints, not by ignoring them . Company Location: United States.