I'm a Senior Software Engineer at UKG with 7+ years designing and operating scalable backend, data, and analytics systems in enterprise production environments. I maintain and extend an established production application using Angular, C#, and SQL while developing AI agents to improve internal developer workflows.
Previously at Intel, I shipped production analytics services, ML-enabled data pipelines, GenAI-powered developer tooling, and CI/CD automation. I hold an M.S. in Computer Engineering from Georgia Tech, and my core background is in C# and Python.
I lead small teams, mentor junior engineers, and treat shipping as a craft. I'm currently open to new opportunities and would love to connect if you're building something ambitious.
Large-scale ETL, feature engineering, statistical analysis, reliability modeling.
RAG systems, multi-LLM orchestration, production model integration, developer assistants.
Distributed services, REST APIs, internal platforms, full-stack feature work.
CI/CD ownership, container deployments, infrastructure for production analytics platforms.
An open-source web app for managing Raid: Shadow Legends clan siege assignments — self-hostable anywhere Docker runs.
Drag-and-drop assignment board with an auto-fill algorithm, a real-time validation engine, PNG battle card generation via Playwright, and Discord DM notifications. Reference deployment runs on Azure Container Apps behind Discord auth.
An LLM-powered job search pipeline that fetches listings from 9 sources, scores each description against your skills profile, and surfaces ranked results in a local web UI.
Multi-provider scoring (Claude, GPT-4, Gemini) with cost-per-call awareness and provider failover. Data stays local. One external contribution merged — a DB query optimization from a community fork.
A terminal-based AI agent that triages support tickets across HackerRank, Claude, and Visa product corpora. Built solo for HackerRank Orchestrate (May 2026, 24 hrs); judged 65th of 12,885 participants across 1,349 submissions.
Nine-stage RAG pipeline — preprocess → safety → router → query expansion → classifier → retrieval → product-area resolution → abstain → generate — with per-stage unit tests, structured run tracing, and explicit abstention on out-of-corpus or high-risk tickets. Multi-provider LLM client with deterministic outputs.
A 4-iteration empirical study quantizing Qwen3.5-0.8B for an agent on a CPU-only consumer-class envelope (8 threads, 16 GB).
Falsified the bandwidth-bound prediction at Iter-1, validated a refined dequant-overhead mechanism at Iter-2, and confirmed a novel KV-noise-as-attention-regularization hypothesis via a directional series. Recommended config: +18–27% decode, −16–31% memory, no quality regression.
Side projects, experiments, and open-source contributions live on my GitHub profile.
// note AI tooling (Claude Code, GPT, Cursor) was used to varying degrees across all of the above — for research, code generation, and validation. Architectural decisions, methodology, and shipped outcomes are mine.
I'm open to senior backend, data, and ML platform roles. Inbox is always on.
POST /hello → christopher_m_beaulieu@outlook.com