Graham Anderson | Full Stack Software Engineer, AI-Native Products

About

Full-stack, from the
Spring Boot service
to the React surface.

I'm a full-stack engineer who builds production features across the whole stack: JVM/Spring Boot services on the backend, TypeScript and React on the front end. At Accenture Federal Services I modernize legacy enterprise systems: containerizing Java/Spring Boot applications, building REST APIs, and deploying services onto OpenShift and Kubernetes.

On the AI side, I build agentic applications on Claude in Python and TypeScript: MCP servers acting as both producer and consumer, tool-calling and conversational agents, RAG pipelines, and real-time streaming interfaces. One of them is an agentic HR operations agent, a data-driven enterprise surface where the interface adapts to the data rather than a static layout. I back them with evaluation harnesses and tests so they stay correct and maintainable as they evolve.

Based in Evergreen, CO, open to relocating for the right team.

Years software engineering

40%

Faster CI/CD deployments

13+

Years leading delivery

$80M+

Programs delivered

Why Me

Built for this
kind of work.

Building an AI-native enterprise product means full-stack engineering, agentic AI, and real ownership in one role, designing the backend and APIs, shipping the interfaces they power, and shaping the patterns the product scales on. That intersection, and the ambiguity of an early product, is where I operate best.

Full-stack ownership, end to end

I build the whole feature, JVM/Spring Boot services behind the API and TypeScript/React on the surface. I take pride in well-tested, maintainable code, and I carry features from design through build and deployment, debugging issues across the stack as they come up.

Agentic AI is the work I already do

I ship production applications on Claude: MCP servers acting as both producer and consumer, tool-calling and conversational agents, sub-agent orchestration, and real-time streaming. One is an agentic HR operations agent, a full AI-native enterprise surface, built end to end. Every project below is live and open-source, not a demo recording.

Data model to pixels, with AI in the loop

I want the breadth that runs from schema to UI. I build data-driven interfaces that adapt to the data rather than static layouts, and I use AI coding tools like Claude Code daily as a first-class part of how I ship, real fluency, not an experiment.

JVM depth meets cloud-native operations

5+ years of Java/Spring Boot engineering: services, APIs, and data models that hold up in production, plus hands-on understanding of JVM behavior, concurrency, and data-access patterns. I've modernized legacy enterprise systems end-to-end on AWS, OpenShift, and Kubernetes, and cut deployment time 40% with parallelized, cached CI/CD.

Projects

Things I've built

JVM + React + MCP

Spring Boot MCP Agent

A full-stack agentic developer tool: a Java 21 / Spring Boot backend publishes tools over an MCP-style producer surface (tools/list, tools/call) and runs a streaming agent that consumes them, with a React + TypeScript front-end that renders tool calls and tokens in real time over SSE. Includes an OpenAI-compatible /v1/chat/completions endpoint and a JUnit suite covering the tools, registry, agent logic, and controllers. The LLM seam is isolated so a real Claude tool-use call drops straight in.

JavaSpring BootReactMCPSSE StreamingJUnit

Live demo is on a free tier and cold-starts, so first load can take 30 to 60 seconds to wake.

Model Context Protocol

MCP Integration Server

Enterprise MCP server exposing 6 agentic tools over both stdio and Streamable HTTP transports, built as both a producer of tools and a consumer of the protocol. The live demo runs a Claude agent as a real MCP client: it discovers tools at runtime over the protocol, then calls them to handle customer lookups across 5 accounts, surface support tickets, search a 5-document knowledge base, and retrieve live business metrics ($5.8M ARR, 1,340 accounts).

MCP SDKStreamable HTTPTypeScriptAgent Tools

Real-Time Streaming

Streaming Analytics Dashboard

A full-stack Next.js dashboard: MRR/ARR, churn, engagement, and segment views, with two real Claude integrations on top: a natural-language query interface that streams answers token-by-token over the live metrics, and server-side cached insight cards. Real-time streaming and a polished React surface over a production data layer.

Next.jsClaude APIStreamingReactTypeScript

Sub-Agent Orchestration

Portfolio Analyst Sub-Agent System

A Python lead orchestrator (Claude Sonnet 4.6, adaptive thinking) dispatches to three specialist sub-agents (Claude Haiku 4.5) via tool-use (market data, news sentiment, risk concentration), then synthesizes their briefings into a decision-grade analyst memo. Backed by a Claude-as-judge evaluation harness scoring routing, coverage, and quality across hand-written cases. Prompt caching on every system prompt and the lead's tool definitions; cache hit/miss telemetry surfaced in the UI.

PythonSub-AgentsClaude APITool UseEvaluation Harness

Agentic HR System

HR Operations Agent

An AI-native take on HR operations: an agentic workflow on Claude with real tool-calling, where the interface is driven by the underlying employee data rather than static layouts. The agent orchestrates 8 tools across 30+ employees, 6 departments, and 7 policies, handling compensation analysis, retention risk scoring, org-chart traversal, and PTO tracking in under 3 seconds per query. Full-stack Next.js / TypeScript, live and open-source, a data-driven enterprise interface built end to end.

Claude APITool UseAgentsNext.jsTypeScriptHR

RAG Pipeline

RAG Knowledge Agent

End-to-end RAG over a documentation corpus: TF-IDF cosine retrieval (smoothed IDF weighting, cached per-chunk vectors) surfaces the top-k chunks with relevance scores, then Claude composes a grounded answer with inline source citations. The retrieve-then-generate pattern behind enterprise knowledge assistants. Both halves are real, no mocks.

RAGTF-IDFClaude APITypeScript

Skills

What I work with

Backend (JVM)

JavaSpring BootREST APIsModular Monolith ArchitectureService Decomposition DesignConcurrency & Data AccessOpenAI-Compatible EndpointsSystems IntegrationSQL

Frontend

TypeScriptReactNext.jsAngular / AngularJSHTML / CSSTailwind CSSData-Driven & Dynamic UIs

AI & Agentic

Claude APITool & Function CallingConversational & Agent-Mediated UXMCP (Producer + Consumer)Agents & Sub-agentsStreaming (SSE / WebSockets)RAGEvaluation Harnesses

Testing & Quality

JUnitClaude-as-Judge EvalsEvaluation HarnessesAPI Governance & Versioning

Cloud & DevOps

AWSKubernetesOpenShift (OCP)DockerGitLab CI/CDHashiCorp Vault

Languages & Delivery

PythonAgile / ScrumCross-Functional Delivery$80M+ Program LeadershipIncident Response

Experience

Where I've worked

Software Engineer

Accenture Federal Services

Mar 2023 – Present

·Modernize a government off-the-shelf (GOTS) application, migrating its stack onto Red Hat OpenShift (OCP) to shorten feature release cycles; containerized its multi-component Java/Spring Boot monolith and deployed it through CI/CD.
·Cut deployment time 40% by parallelizing and caching GitLab CI/CD pipelines, shortening the loop from code change to deployable build.
·Act as Scrum Master for a 5-person engineering team: run Agile ceremonies, coordinate dependencies with partner teams, and report progress and risks up the chain to leadership.
·Build full-stack features from REST APIs to AngularJS front ends, holding to versioning, backward-compatibility, and security standards on public-facing APIs.
·Centralized application secrets in HashiCorp Vault to meet federal compliance requirements.

Software Developer

Modius

Mar 2022 – Mar 2023

·Built Java features with SmartGWT/JavaScript front ends for a DCIM (data center infrastructure management) platform used by hyperscale operators to manage their infrastructure.
·Authored and consumed REST APIs for real-time device communication and integration with customers' enterprise systems.
·Streamlined deployment workflows by optimizing integration scripts, reducing manual handoffs between releases.

Java Full Stack Developer

Skill Distillery

Oct 2021 – Mar 2022

·Built full-stack applications in Java, Spring Boot, Angular, and JavaScript deployed on AWS with RESTful service architectures.
·Served as Scrum Master and Database Administrator, enforcing Agile cadence, facilitating ceremonies, and driving schema design.

Pre-Construction Manager

Commercial & Industrial Electrical Construction

Jan 2008 – Sep 2021

·Led pre-construction on 15 to 20 bids a year ranging from $5M to $85M, winning roughly 1 in 4, and owned scope development, estimating, business cases, procurement strategy, and risk evaluation before mobilization.
·Trained junior estimators, superintendents, and new project managers, building the bench that carried projects from bid to field.
·Coordinated procurement, engineering, manpower, and scheduling into a delivery plan for each awarded project.

GrahamAnderson

Full-stack, from theSpring Boot serviceto the React surface.

Built for thiskind of work.