Senior Agentic AI Software Developer

Kentro

5h•Remote

About The Position

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.

Requirements

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
Public Trust required; ability to obtain higher clearance eligibility preferred
U.S. Citizenship

Nice To Haves

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

Responsibilities

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.
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
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
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

Benefits

We offer competitive benefits package including paid time off, healthcare benefits, supplemental benefits, 401k including an employer match, discount perks, rewards, and more.
We invest in our employees – Every employee is eligible for education reimbursement for certifications, degrees, or professional development.
Reimbursement amounts may fluctuate due to IRS limitations.
We want you to grow as an expert and a leader and offer flexibility for you to take a course, complete a certification, or other professional growth and networking.
We are committed to supporting your curiosity and sustaining a culture that prioritizes commitment to continuous professional development.
We work hard; we play hard.
Kentro is committed to incorporating fun into every day.
We dedicate funds for activities – virtual and in-person – e.g., we host happy hours, holiday events, fitness & wellness events, and annual celebrations.
In alignment with our commitment to our communities, we also host and attend charity galas/events.
We believe in appreciating your commitment and building a positive workspace for you to be creative, innovative, and happy.