AI Agent Developer

Position: AI Agent Developer

Location: Charlotte, NC (3 days onsite)

Duration: 9+ Months

Interview: Video interview

Job Description:

• Most important thing to Manager is finding quality, strong/seasoned engineers
• He is not expecting someone to come in with 10 years of experience building agents on the AI front
• Needs to have a solid understanding of AI coupled with strong foundational coding skills

• Need great people in the following areas: Compute, CD, Support Eng, Dev Prod, Automation, & Agentic

• Compute peeps might be stronger in DevOps/less coding - he would be open to considering that as well

• Manager has found it very challenging to find people with decent programming skills (GoLang, Python, Typescript)

• Each product has their own tech stack/language - if we find someone really solid in one area, he could likely find a place for them

• He understands that a lot of individuals are using AI for coding (and transparently, they do some of that at client as well) - however, they are looking for individuals with true foundational skills & those without will not perform well on the coding assessment
• For the Agentic AI openings, he is not expecting someone to come in with 10 years of experience building AI agents, he is focused on finding strong engineers with a solid understanding of AI (a few years of hands-on experience should be enough)

We are seeking a Senior Agentic Software Engineer to design, build, and operate production-grade AI agent systems that augment and automate real business workflows.

• This role goes beyond prompt engineering or demo-level prototypes. You will own agentic systems end-to-end—from architecture and integration with existing services, to reliability, evaluation, and long-term operation. You’ll work closely with product, platform, and domain experts to deliver agentic capabilities that are trustworthy, scalable, and measurable, while helping define how agentic systems are built across the organization.

What You’ll Do     

• Design, build, and operate agentic systems that reliably complete real tasks, not just answer questions.
• Architect agents that support planning, memory, tool use, and multi-step execution, selecting appropriate patterns (single-agent, multi-agent, workflow-driven, human-in-the-loop) based on problem constraints and risk.
• Balance autonomy with control by designing agents that are predictable, debuggable, secure, and aligned with business goals.
• Build agents using modern frameworks (e.g., LangGraph, LangChain, Semantic Kernel, AutoGen, or equivalent), implementing structured outputs, tool-calling, reflection, and state management.
• Design and implement MCP- and/or RAG-based integrations as first-class mechanisms for how agents access tools, data, and context.
• Enforce security, consent, access control, and observability across all agent–tool interactions, partnering with platform teams to establish and evolve MCP integration standards.
• Integrate agentic systems into existing services and platforms via APIs and backend services, owning production readiness end-to-end.
• Define what “good” looks like for agents using clear metrics (e.g., accuracy, success rate, latency, cost, failure modes), and use those metrics to drive continuous improvement.
• Build automated evaluation pipelines (offline tests, synthetic data, regression checks) and instrument agents with tracing, logging, and observability to support debugging and iteration in production.
• Design fallback, recovery, and human-escalation mechanisms for failure scenarios, proactively identifying and mitigating failure modes.
• Establish architectural standards and best practices for agentic development, raising the technical bar through design reviews, documentation, mentorship, and knowledge sharing.
• Partner with product and domain stakeholders to shape solutions, make informed trade-offs, and ensure agentic systems deliver meaningful business impact.

Domain / Problem Space

• You will work on agentic systems in the context of:
• Experience with internal developer portals like Backstage with associated patterns like GitOps, API-driven microservices, paved paths, and more
• Experience with design patterns in Kubernetes like controllers, control planes, operators, and more
• Work on container orchestration, infrastructure as code (IaC), and CI/CD pipelines for deploying and managing k8s instances.
• Monitor the performance of developer platform, identify potential issues, and ensure high availability of the platform.
• Using Infrastructure As Code (IAC) best practices, create automated infrastructure within the cloud and on-premise platform, including package management, application load and configuration, and systems monitoring and administration.
• Deliver improvements to source code management, deployment, operations, maintenance, cost control, security, monitoring, and audit tools and processes.  
• Implement and maintain CI/CD tools and processes to support development, QA, and customer value realization teams.
• Manage a service critical codebase with version control using Git including Gitlab, or  Github
• These domains require agents that operate on real, evolving data, integrate deeply with existing systems, and meet a high bar for correctness, traceability, and user trust.

Required Experience

• 5+ years of professional software engineering experience, with a strong backend or systems background.
• Proven experience building LLM-powered applications beyond prototypes.
• Hands-on experience designing and implementing agentic systems, including agents, workflows, MCP-based tool integration, and RAG.
• Strong proficiency in Python (or similar agent-oriented languages) and experience building production APIs or services.
• Experience designing systems with observability, evaluation, and operational ownership in mind.

Thanks

Krish