Giannis Roussos

Available to hire

I'm Giannis Roussos, a full-stack software engineer based in Athens, Greece. I design and ship scalable SaaS platforms and AI-integrated systems using TypeScript, React, Next.js, and Node.js.

About

I’m Giannis Roussos, a full-stack software engineer based in Athens, Greece. I design and ship scalable SaaS platforms and AI-integrated systems using TypeScript, React, Next.js, and Node.js. I enjoy building practical, maintainable architectures and collaborating across product and design teams to deliver solid user experiences.

I’ve led end-to-end production builds, rebuilt system architectures for reliability and performance, and delivered real-time dashboards and AI-powered integrations while prioritizing security, accessibility, and clean code. I thrive in fast-paced environments and love turning complex requirements into elegant, working solutions.

  • Joined April 2026

Languages

  • EnglishFluent
  • Greek, ModernFluent
  • Spanish; CastilianIntermediate
  • GermanIntermediate
  • FrenchIntermediate

Industry experience

  • Software & Internet
  • Healthcare
  • Professional Services
  • Travel & Hospitality
  • Other
  • Education

Projects · 3

Multi-model AI clinical decision support platform built independently in both Next.js and Ruby on Rails to benchmark architectures.

What it does
Clinicians paste medical records and receive distilled summaries, suggested differential diagnoses, treatment options, and live evidence from PubMed — all grounded in the document context only, with no external knowledge injection (hallucination eliminated by design).

Architecture highlights

  • Five-model Gemini/Gemma waterfall cascade (Gemini 2.5 Flash → Flash Lite → three Gemma variants)
  • Reactive 429/503 switching with capability detection between Gemini and Gemma model families (Gemma does not support the systemInstruction field — handled with a runtime supportsSystemInstruction() check)
  • 45-second AbortSignal timeout per call
  • RAG via Supabase pgvector with a pure-TypeScript cosine-similarity fallback path for RPC failures
  • HL7 FHIR R4 data explorer and raw .hl7 file ingestion alongside PDF and text
  • Live PubMed evidence grounding for clinical claims
  • Redis rate limiting, Zod schema validation, structured audit logging

The Rails benchmark
Rebuilt the entire system in Ruby on Rails over a single weekend (framework learned from scratch) to compare architectures. Result: 60% faster total execution (5.6s vs 14.7s), 85% reduction in JavaScript payload.

Stack: TypeScript, Next.js (App Router), Ruby on Rails 7, Supabase (Postgres + pgvector), Vercel AI SDK, Redis, Zod, Hotwire (Turbo/Stimulus), Vercel, Fly.io

Live demos:

Source: https://www.twine.net/signin

Real-time patient vitals dashboard pulling HL7 FHIR R4 data through a Node.js/Express proxy on AWS App Runner.

Why it exists
Built from the perspective of an ICU nurse who saw firsthand how fragmented and slow FHIR data delivery is in production hospital environments. The goal: prove that clean server-side data transformation can deliver a responsive clinical dashboard without overloading the browser.

Technical highlights

  • Custom SVG waveform rendering for live patient vitals
  • Server-side data transformation reducing client-side processing overhead by 30%
  • Node.js/Express proxy layer running on AWS App Runner
  • Environment-driven configuration for multiple FHIR sandbox sources
  • React/Next.js frontend with responsive design across desktop and tablet form factors

Stack: TypeScript, Next.js, Node.js, Express, AWS App Runner, HL7 FHIR R4, SVG

Live demo: https://www.twine.net/signin
Source: https://www.twine.net/signin

  • Back-End Developer
  • Front-End Developer
  • Full Stack Developer

AI selfie-capture module built during a paid software engineering internship at Skinstric. Iterated from naive pixel-based detection to a production-grade implementation that ships well beyond the original Figma spec.

The technical core
A real-time visual feedback ring of 36 independent arc segments around an oval, each lighting up as the user’s face aligns with it. Built from first principles — no library handles this specific combination of geometry, smoothing, and rendering.

Implementation details

  • BlazeFace bounding box geometry with mirror correction for the front-facing camera (scaleX(-1) on the video element flips raw coordinates — corrected before segment math runs)
  • Per-segment confidence calculation: angle the segment occupies, find the corresponding point on the oval and on the face bounding-box ellipse, measure normalized distance, convert to confidence
  • Centering score multiplier so segments only fully illuminate when the face is both well-sized and well-centered
  • Asymmetric temporal smoothing (0.4 rising, 0.25 falling) and spatial smoothing across neighboring segments for a fluid 30fps animation
  • Rendered as a conic-gradient built from 36 per-segment RGBA values, masked with a radial gradient so only the 4px border ring shows color
  • Firebase Cloud Storage integration for capture upload and admin dashboard

Stack: TypeScript, Next.js, React, MediaPipe BlazeFace, Firebase Cloud Storage, Browser Media API, SVG, Conic Gradients

Live demo: https://www.twine.net/signin
Source: https://www.twine.net/signin

Work experience· 7 roles

Software Engineering InternJan 2026 – Feb 2026 · 2 mos

AI selfie-caption module using MediaPipe BlazeFace for real-time face detection, evolving from pixel-based detection to production-grade 36-segment landmark alignment feedback. Stack: React, Next.js, TypeScript, Firebase, Browser Media AI.

Freelance Software Engineer · Hestia's Hearth LLCJan 2026 – Present · 11 mos

Designed and shipped AI-enabled clinical decision support using Gemini/Gemma architecture, RAG via Supabase pgvector, PubMed grounding, FHIR4 explorer, Redis rate-limiting. Rebuilt Ruby on Rails stack for faster performance (60% faster) and reduced client-side JS payload by 85%. Built FHIR Pulse real-time clinical dashboard with SVG rendering and a Node.js/Express proxy on AWS App Runner, reducing client-side processing overhead via server-side data transformation. Developed Python/OpenAPI 3.0 static analysis tool integrated with GitHub Actions as CI/CD gate for API security compliance.

Software Engineering Intern · Hestia's Hearth LLCDec 2025 – Feb 2026 · 3 mos

AI selfie-capture module using MediaPipe BlazeFace for real-time face detection, iterating from pixel-based detection to a production-grade 36-segment live-alignment feedback system.

Software Engineer Intern · SummaristDec 2025 – Jan 2026 · 2 mos
Critical Care and Emergency Registered Nurse (Travel and Staff) · AMN Health Care / Health Trust Workforce SolutionsJan 2017 – Jan 2025 · 8 yrs 1 mo
District and Regional Sales Manager · InterFace / DriveTime / Diageo / AmeriBank (as listed on resume)Jan 2007 – Jan 2015 · 8 yrs 1 mo
District and Regional Sales Manager · InterFACE / DriveTime / DiaGeo / AmeriBankJan 2007 – Jan 2015 · 8 yrs 1 mo

Education· 6

Software Engineering Program · FESI Institute2030 – 2026
B.S. Nursing · University of West Florida2030 – 2026
B.S. HR Management · Oakland University2030 – 2026
Software Engineering Program · FESI Institute2030 – 2026

Certifications and awards

Registered Nurse2026
ACLS Provider2026

Hire Giannis Roussos today

Post a job and invite Giannis, or contact them directly. No hidden commission.

Post a job