• Build and optimize agentic systems and multi-agent workflows for real-world applications. • Develop tailored LLM pipelines using frameworks such as LangChain, LangGraph, and related ecosystems. • Deploy and optimize open-source LLMs using vLLM, TGI (Text Generation Inference), and Python-based inference stacks. • Work with diverse open models (Qwen, Llama, Mistral, etc.) including fine-tuning, evaluation, and integration. • Implement scalable AI services with robust prompt engineering, autonomous task planning, and tool execution. • Collaborate with cross-functional teams to define architecture, performance goals, and best practices.

• Drive strategic AI initiatives that directly impact client success and business growth, defining technical roadmaps and influencing product strategy to solve complex enterprise problems. • Architect and enhance our agentic processes for enterprise-scale deployments, building sophisticated multi-agent orchestration patterns for complex workflows. • Design advanced agent memory systems and context management solutions that maintain coherence across long-running conversations and extended enterprise tasks. • Build and implement RAG (Retrieval-Augmented Generation) systems to dramatically improve AI accuracy, including knowledge retrieval pipelines and semantic search optimization for large-scale datasets. • Develop enterprise-grade MCP (Model Context Protocol) services enabling seamless client agent integration with standardized APIs, security protocols, and comprehensive documentation. • Leverage AWS technologies (Bedrock, Lambda, etc) to architect AI solutions with optimal performance, cost efficiency, and enterprise-scale LLM integration. • Design and optimize schemas for storing LLM interactions, agent state, and conversation history while building monitoring systems for AI operations. • Lead cross-functional initiatives to integrate AI throughout our platform ecosystem, partnering with product and engineering teams to deliver measurable business value. • Translate complex technical AI concepts into business value, working directly with enterprise clients to understand their needs and influence strategic platform decisions. • Mentor engineering teams on AI best practices, emerging technologies, and enterprise AI governance while maintaining high engineering standards for production AI systems.

• Be the lead AI technical expert in strategic sales pursuits. • Translate Granicus’s AI capabilities to real-world challenges faced by government agencies. • Work alongside sales, product, and customer experience teams to design solutions. • Deliver proofs of concept and support delivery of AI solutions. • Align technical requirements to business outcomes to increase win rates.

• Design and deliver production-grade agentic AI systems on Azure AI Foundry, ensuring solutions go well beyond PoC and into scalable, enterprise-ready platforms. • Architect end-to-end pipelines leveraging Azure OpenAI, vector search, tool-calling patterns, and LangChain / Semantic Kernel for orchestration. • Define and enforce REST API design standards, JSON schema definitions, and event/message-based integration patterns across AI workloads. • Lead the evolution of solutions from MVP to productized platforms, including refactoring, hardening, and meeting non-functional requirements around performance, reliability, observability, and security. • Deploy and oversee scalable Azure infrastructure (AKS, App Service, Functions, or equivalent), collaborating with DevOps/SRE teams to define runbooks, SLIs/SLOs, and monitoring frameworks. • Evaluate and integrate emerging agent frameworks and patterns (MCP, A2A) to continuously modernize platform capabilities. • Use LangSmith or equivalent tooling to implement tracing, evaluation, and quality assurance across agentic pipelines. • Document architectures, sequence diagrams, and interaction flows using Visio, Figma, or similar tools; facilitate collaborative design sessions using Mural/Miro with distributed teams. • Partner with cross-functional and multi-program teams to ensure platform components are reused and versioned effectively across products. • Support incident management and post-mortems, contributing to a culture of continuous improvement in live production contexts.