Application Architect, IT - Architects

Ascensus•Lake Mary, FL

About The Position

As an Application Architect in the Enterprise AI Program, you will provide technical direction, architectural oversight, and hands-on engineering leadership across scrum teams building production AI-enabled software. This role sits between enterprise/program architecture and delivery teams, helping translate business needs and platform strategy into practical, scalable, secure, and maintainable technical solutions. This is a senior technical leadership role for someone who can shape architecture and implementation patterns, guide teams building AI-enabled applications, agents, workflows, and integrations, validate technical direction through code, demos, and proofs of concept, establish reusable patterns, templates, and reference implementations, stay close to the codebase through code reviews, technical spikes, troubleshooting, and situational code contributions, and evaluate emerging AI technologies and educate the team through practical examples. This role is not a full-time feature development position, but it is also not a hands-off architecture role. The Application Architect is expected to remain technically close to the platform and contribute directly when architectural complexity, delivery risk, production issues, or emerging platform patterns require senior technical involvement. You will help lead architecture across Enterprise AI platform capabilities, LLM-powered agents and agent workflows, Retrieval-Augmented Generation (RAG) patterns, Model Context Protocol-style tool integrations, durable workflow and orchestration patterns, internal and external AI-enabled applications, secure integrations with Salesforce and internal Ascensus systems, observability, evaluation, testing, and production support patterns, and AI-assisted engineering practices using tools such as Cursor, Claude Code, or similar platforms. We are looking for an architect who is practical, hands-on, delivery-oriented, and deeply curious about where AI engineering is headed. You should be able to set direction without creating unnecessary complexity, mentor engineers without becoming a bottleneck, and turn emerging technology into working examples that help teams move faster with confidence.

Requirements

8+ years of professional software engineering experience.
2+ years in a technical lead, application architect, solution architect, staff engineer, or comparable technical leadership role.
Bachelor’s degree in Computer Science, Computer Information Systems, Business Information Systems, a related technical field, or equivalent practical experience.
Strong experience designing, building, and supporting production software in medium to large business environments.
Demonstrated ability to remain hands-on with the codebase through code reviews, proof-of-concept development, technical spikes, complex troubleshooting, and direct code contributions.
Experience building proofs of concept, reference implementations, technical demos, templates, or reusable engineering patterns.
Strong experience with modern software engineering practices, including: Clean code, Source control, CI/CD, Automated testing, Design patterns, Refactoring, API design, Observability, Production support.
Strong experience with one or more modern programming languages and platforms, such as: Python, JavaScript / TypeScript, SQL, Similar modern development platforms.
Experience designing distributed systems, service integrations, APIs, workflow logic, or platform capabilities.
Experience with LLM-powered systems or AI-enabled applications, such as: RAG, Chatbots, Agent workflows, Prompt engineering, Tool use, AI-assisted application development.
Strong understanding of architecture principles, including: Modularity, Reusability, Scalability, Reliability, Security, Maintainability, Observability, Cost awareness.
Experience guiding teams through technical design, estimation, implementation, and production readiness.
Strong troubleshooting and root-cause analysis skills across application code, integrations, logs, traces, telemetry, and production behavior.
Experience mentoring, coaching, and influencing engineers without requiring direct reporting authority.
Excellent communication skills with the ability to explain technical tradeoffs to engineers, product partners, business stakeholders, and senior leaders.
Comfort operating in ambiguous, fast-moving environments where AI capabilities, tools, and platform patterns continue to evolve.

Nice To Haves

Enterprise AI platform architecture
Azure AI Foundry, Azure AI services, or similar cloud AI platforms
Azure DevOps, Azure App Service, Azure API Management, or related Microsoft cloud tools
LLM application architecture using models from OpenAI, Anthropic, Microsoft, or similar providers
Agentic applications and multi-agent workflow patterns
RAG architecture, retrieval quality, chunking strategies, embeddings, vector databases, and reranking
Model Context Protocol, function calling, tool calling, or enterprise tool integration patterns
MCP registry, tool governance, tool security, or act-as-user integration patterns
Durable workflow platforms such as Temporal
Event-driven systems, message queues, or orchestration patterns
Salesforce integrations or enterprise system integrations
Observability platforms such as Langfuse, New Relic, OpenTelemetry, Azure Log Analytics, or similar tools
AI evaluation frameworks, golden tests, prompt/version management, or quality measurement practices
Secure software design for systems that handle sensitive or regulated data
DevOps, infrastructure, deployment automation, containerization, or cloud-native application patterns
AI-powered development tools such as Cursor, Claude Code, or similar tools
Creating technical demos, POCs, or internal enablement materials to help engineering teams adopt new technologies
Technical documentation, architecture decision records, solution diagrams, and executive-level technical communication
Working with SDETs, DevOps engineers, support engineers, software managers, product owners, and enterprise architects

Responsibilities

Set technical direction for AI platform capabilities and implementation patterns.
Partner with other architects to align team-level designs with broader platform strategy.
Ensure solutions are secure, scalable, reliable, observable, and maintainable.
Help teams make good tradeoff decisions around speed, quality, complexity, cost, and long-term supportability.
Guide architecture for LLM-powered agents, RAG pipelines, prompts, skills, tools, and workflows.
Define reusable patterns for AI application development.
Establish standards for tool integrations, orchestration, observability, evaluation, and production readiness.
Support responsible AI engineering practices that improve accuracy, transparency, reliability, and user trust.
Stay close to the codebase through regular code reviews, design reviews, POCs, reference implementations, and complex troubleshooting.
Contribute directly to application, platform, workflow, integration, or agent code when senior technical involvement is needed.
Build working demos, technical spikes, starter templates, and reference implementations.
Experiment with emerging AI technologies, tools, models, frameworks, and orchestration patterns.
Turn technical exploration into practical team guidance and reusable implementation standards.
Assist with production issues requiring senior engineering judgment.
Use hands-on learning and code-level involvement to coach engineers and raise the technical bar.
Work closely with program architects, application architects, software managers, engineers, SDETs, DevOps engineers, support teams, product partners, and business stakeholders.
Explain architecture decisions and tradeoffs clearly.
Document solution designs, patterns, diagrams, standards, and decision records.
Promote reuse and consistency across teams.
Help socialize new technologies, patterns, and platform capabilities.
Set clear technical direction that teams can actually execute.
Help teams move faster without creating unnecessary complexity or long-term risk.
Build reusable patterns that improve consistency, quality, and delivery speed.
Make AI platform capabilities easier for teams to understand, use, test, and support.
Remain close enough to the codebase to make architecture decisions that are practical, credible, and executable.
Contribute directly when the team needs senior technical help.
Turn emerging AI technologies into practical examples, demos, and reusable patterns.
Mentor engineers and raise the technical bar across teams.
Communicate architecture in a way that is useful to engineers, leaders, and business partners.
Help the Enterprise AI Program scale from individual solutions to a repeatable platform model.