The Opportunity

This is an individual-contributor architecture role, and a deliberately hands-on one. You will spend most of your time designing and building - prototyping, writing production code and infrastructure, and working directly in the codebases involved. You will also spend meaningful time with product teams across the company, each with its own architects, roadmap, and deep domain expertise, where your influence will come from collaboration and demonstrated results rather than from reporting lines.

Expect variety. A given week may include architecture and design work, implementation, embedding with a product team to resolve a dependency, and presenting ideas to internal stakeholders and to customer design partners.

What You'll Do

Design and build agent systems. Core reasoning loops, planning, state and memory management, tool interfaces, sub-agent delegation, and orchestration for multi-turn and autonomous agents.

Make agent output trustworthy enough to act on. This is central to the role rather than a final compliance step:

• Confidence scoring and routing - determining what can proceed automatically, what warrants a brief human review, and what requires a person to handle directly
• Human-in-the-loop design that keeps professional judgment, and accountability, with the practitioner
• Audit trails and explainability sufficient to withstand evidentiary and public-records scrutiny
• Evaluation practice: golden datasets, regression gates on model and prompt changes, staged and canary rollout, comparison of candidate models against those in production, and monitoring for drift after release
• Adversarial and failure-mode design: prompt injection and jailbreak threat modeling, containment of the effects of an incorrect action, deterministic controls around probabilistic components, and clear decisions about capabilities we choose not to build
• Agent-level observability from the outset - which model call, which tool, which inputs, and the basis for the agent's decision

Make the existing portfolio accessible to agents. Our products span a wide range of technologies, from modern .NET and Python services to long-lived platforms that predate current frameworks. You will build MCP servers, APIs, wrappers, and adapters that expose product capability to agents; contribute to the data pipelines and ingestion layers that feed them; and help instrument existing applications to understand how they are used today.

Partner across product teams. You will work alongside architects and engineering leaders who know their products deeply. Depending on the situation, that may mean designing a solution with a team and supporting them as they build it, or coming up to speed on their stack and delivering the work yourself - then walking the team through the approach so they can carry it forward.

Engage with customers. Work with our design partner agencies and end users to ground the work in real operational practice, and bring what you learn back into the design.

Model current AI-assisted engineering practice. You will bring a well-developed harness of your own: skills and commands, hooks, MCP servers, sub-agents, specification-driven workflow, and deterministic quality gates - compilers, test suites, static analysis, custom lint rules, and architecture-conformance checks - so that non-deterministic tooling produces predictable, standards-conforming output. Teams you work with will learn a great deal simply from how you work.
Skills & Requirements
Required Qualifications

• 10+ years building and shipping production software, including 3+ years at architect or staff-engineer scope spanning multiple teams or products.
• Current, daily, hands-on experience with agentic development tooling. You work in Claude Code or an equivalent agentic environment as a matter of routine; you have built skills and commands, hooks, MCP servers, and sub-agents; you run specification-driven workflows; and you hold well-formed views on context and harness design drawn from practice. We will ask you to walk us through how you work.
• Experience designing LLM-based systems that produce reliable output: grounding and retrieval, structured output, confidence handling, hallucination control, human-in-the-loop patterns, and evaluation.
• Polyglot and stack-agnostic in practice. Depth in at least one of C#/.NET, Python, or TypeScript, together with a demonstrated pattern of becoming productive quickly in unfamiliar technologies, including older ones.
• Strong cloud architecture experience on a major public cloud. We run on AWS; deep Azure or GCP experience with a clear ability to translate is welcome.
• Experience making legacy systems programmable - APIs, wrappers, adapters, or protocol-level interfaces such as MCP over systems that were never designed for them.
• Observability as a first-class concern: distributed tracing, structured logging, and metrics, along with the agent-level equivalent.
• Containers, infrastructure-as-code (Terraform or equivalent), and CI/CD pipeline design. Everyone on this team works with infrastructure.
• A track record of leading through influence rather than authority, alongside senior technical peers outside your reporting line.
• Clear written communication. Specifications, architecture decision records, and design documents are primary artifacts of this role, for human and agent readers alike.

Preferred Qualifications

• Experience delivering an agent to production that takes action on a user's behalf, including confidence gating, review, and rollback.
• Experience in a regulated or high-consequence domain: public safety, healthcare, financial services, criminal justice, or government.
• Model-level work: fine-tuning, LoRA, distillation, local or self-hosted models, and cost and latency optimization.
• Data platform work: lakehouse layering, ingestion pipelines, and entity resolution across disparate source systems.
• Multimodal experience - audio and speech, video, or sensor fusion.
• Personal or open-source projects demonstrating sustained, self-directed work with agent tooling.

CJIS Clearance

A required part of the onboarding process for this role involves obtaining CJIS (Criminal Justice Information Services) clearance-a critical credential for safeguarding public safety data. At CentralSquare, we'll stand with you every step of the way to secure this clearance should you be selected for hire. As part of the process, a comprehensive background check will be conducted, and please note that U.S. citizenship or permanent residency is generally required to obtain CJIS clearance.

Qualifications