AGAdrian Góra CV PDF

Available from 1 Nov 2026 · Poland · remote or hybrid

Adrian Góra

AI Engineer for manufacturing and engineering data

I build AI tools for manufacturing teams: document search that cites its sources, meeting and translation pipelines, and quoting from CAD models. Six years in software and three and a half in automotive CAD engineering.

Download CV PDF Email me LinkedIn GitHub

CV po polsku: PDF · wersja web

55% → 84%top-1 page retrieval after adding hybrid search to visual RAG 99,933LLM judgments in 3 minutes over 7,040 translation keys 2,200+commits in the last 12 months, most of them in private repos 5internal AI tools built at a manufacturer since February 2025

01Current role

Shipped at Wiśniowski

AI Engineer (official title: Specjalista ds. AI), Feb 2025 – present. Internal AI tools for a Polish manufacturer of industrial doors, gates and fences. The code is private; I can walk through any of it in an interview.

  1. Company-wide RAG assistant

    Deployed RAGFlow on a Linux server and connected it to Open WebUI as the company chat. It answers from a large set of complex technical PDFs. Telemetry and monitoring are built for EU AI Act compliance.

    • RAGFlow
    • Open WebUI
    • Linux
    • Telemetry
    • EU AI Act

  2. Microsoft Teams meeting pipeline

    Scans one group's meetings in on-premises Outlook and switches on automatic recording. Transcripts and recordings come in through Microsoft Graph (webhooks and polling), and an LLM turns them into structured JSON reports.

    • Microsoft Graph
    • Outlook on-prem
    • TypeScript
    • Node.js
    • LLM

  3. AI translation portal

    Built an internal portal to replace lokalise.com. Gemini pre-translates every key, translators accept or fix it, and missing keys are flagged. Our texts exist in many languages and must stay consistent, so I added statistics, helpers for translators and an automatically generated starting glossary. Every decision is logged, so we can see how often the AI gets it right.

    • TypeScript
    • Gemini
    • OpenAI
    • Redis

  4. Process-route analytics

    Working on a prototype that lets engineers chat with historical production traces, test new settings and get suggested routes. A deterministic core computes the numbers, and experimental modules add an LLM and autoresearch.

    • Go
    • Python
    • LLM
    • Autoresearch

  5. AI interviews for process improvement

    Runs on the Gemini managed-agents sandbox. After a 15-minute voice or text interview about someone's daily work, it writes an automation report, adds what it learned to an LLM wiki, and turns repeatable tasks into SKILL.md files for agents.

    • Gemini managed agents
    • TypeScript
    • LLM wiki
    • SKILL.md

02Selected projects

Projects with code you can read

Public repositories first, each with a link to the code. The private ones below them I can show on a call.

Public code

Visual RAG for technical PDFs

Finds the right page in product catalogues and technical PDFs by how the page looks (drawings, tables, dimension callouts), then answers from the page images with a vision model and cites the page.

55% → 84%
top-1 page, visual-only vs hybrid
100%
recall with LLM page reranking
p = 0.001
hybrid beats visual 11–0 where they disagree
  • Benchmarked 7 retrieval modes on 38 questions whose gold page is verified by string match (114 in the full set), with Wilson intervals and an exact McNemar test for every pair.
  • Hybrid search (pixel index + BM25, fused with reciprocal rank fusion) raised top-1 from 55% to 84%. The same benchmark showed that a paid query-expansion stage added nothing, so the default mode skips it.
  • Web UI and API with a per-question retrieval mode, page citations and an answerability score.

Thin layer over PixelRAG (StarTrail): retrieval modes, hybrid search, evaluation and UI are mine.

  • Python
  • FAISS
  • BM25 + RRF
  • PixelRAG
  • Gemini
  • Claude
Code and benchmark
Public code

CAD quoting engine for machined parts

Quotes a machined part from its STEP model for a tool shop. Code measures the geometry and computes the price; the language model reviews technology and risks the way a shop manager would.

STEP → PLN
geometry from OpenCASCADE, price from shop rates
3 states
pass, fail or need-info on every check, each citing its source
  • Volume, mass, envelope and cost-driving features come from OpenCASCADE. Price is machining time × shop rate, and a physics-based floor on cutting time stops the model from inventing hours.
  • Preflight marks each check pass, fail or need-info with a cited source (ISO 2768, ISO 286, material data). Any fail or missing input makes the quote non-binding.
  • Web app for estimators who don't program: 3D preview, 2D drawing input, editable rates, print to PDF and a make-or-buy check against SendCutSend. Covered by 8 test modules.

My wycena skill inside a fork of the MIT-licensed text-to-cad library.

  • Python
  • OpenCASCADE
  • build123d
  • trimesh
  • ezdxf
  • Claude / OpenAI
Code
Public code

LLM-judged translation audit

Finds inconsistent terminology in a translation corpus that never had a glossary. Code mines the disagreements across 7,040 keys and an LLM judge settles each one.

99,933
judgments in 3 minutes
~300 ms
check on every edit in the review app
  • Exports an Excel workbook for sign-off and a keyboard-driven review app where translators curate the glossary; decided terms are never re-arbitrated.
  • Sibling demo judge-sheets: type a column header such as Urgency and 300 rows fill with semantic predictions in about 3.5 s, as =JUDGE, =PICK and =RATE formulas you can inspect in the formula bar.
  • TypeScript
  • TypeSafe Jev
  • Excel
Code
Public code

Multi-agent pricing playground

Four Bun workspaces on the Vercel AI SDK: a tool-calling calculator agent, a coding REPL with per-tool confirmations, an eBay pricing agent (parse → search → compute → present) and a web server that streams the agents over SSE.

  • TypeScript
  • Bun
  • Vercel AI SDK
  • Claude
  • OpenAI
  • eBay API
Code
Public code

Streaming ML demo, hackathon 2nd place

Live Binance trades through the Streamr network, ARIMA forecasts on the stream, results on a chart. 2nd place at the LearnWeb3 AI Hackathon.

  • Node.js
  • Streamr
  • ARIMA
Code

Private repositories

Private repo

Cairn: evidence CLI for process routing

Answers where work waits, where it loops back and which routing choice succeeded more often with the work mix held fixed. Each claim carries its sample size, basis and whether it may be quoted, and findings can be re-proved on new data. Output is one JSON envelope per call, built for AI agents first. Includes a robot-fleet dispatch testbed (VDA 5050).

  • Go
  • BPMN
  • VDA 5050
Private repo

PDF wiki

Local-first knowledge base: drop in a PDF, run ingest, get a cross-linked Markdown wiki with semantic search. Claude vision describes every figure.

  • TypeScript
  • Claude
  • qmd
Private repo

Robot arm control in the browser

Calibration and daily control of a LeRobot SO-ARM100 from a laptop or phone: keyboard and gamepad input, an e-stop, and a single owner for the serial port.

  • Python
  • LeRobot
  • WebSockets
Private repo

HAR to API brief

Record browser traffic once and get a brief for rebuilding the API outside the browser: auth, endpoints, body shapes and curl templates.

  • Python
Private repo

meat: reading diffs

Turns a large code diff into a smaller reading diff focused on the consequential changes. TypeScript CLI, migrated from Go.

  • TypeScript
  • Go

Earlier experiments

03How I work

Engineering principles

P1

Code computes, the model judges

In the quoting engine, geometry and price come from code and the LLM reviews technology and risk. Any number a model could guess is computed instead.

P2

Measure before claiming

Retrieval modes ship with a benchmark, confidence intervals and significance tests. When two rows can't support a conclusion, the README says so.

P3

Build for the person at the desk

Translators accept or correct AI proposals and every decision is logged. Estimators get a web app with editable rates and a printable quote.

P4

Tools agents can use

CLIs return one JSON envelope with the answer, caveats and the next calls to make. My recent repos include an AGENTS.md for coding agents.

04Career

Experience

  1. Feb 2025 – present

    AI Engineer Wiśniowski

    Official title: Specjalista ds. AI. Internal AI tools for a Polish manufacturer of industrial doors, gates and fences. Five internal AI tools, described in Shipped at Wiśniowski.

  2. Aug 2023 – Jan 2025

    Software Engineer Freelance

    • Prototyped AI tools (predictive models, chat over documents) to test product ideas, and shipped a staking app UI for web and mobile (TypeScript, React, ethers). Took 2nd place at the LearnWeb3 AI Hackathon.
  3. Jun 2023 – Aug 2023

    Full-Stack Engineer Playdate App Limited

    • Built release version control so users on outdated iOS and Android builds could be migrated, fixed a critical Android onboarding bug and owned CI/CD on AWS Elastic Beanstalk (React Native, Django).
  4. Dec 2022 – Jun 2023

    Software Engineer Ariable

    • Delivered the front-end MVP of an NFT perpetual trading platform and a real-time Node.js + PostgreSQL watcher for on-chain transactions. Also reviewed the Solidity contracts.
  5. Dec 2020 – Dec 2022

    Frontend Engineer BlockchainWares Software

    • Built balance, contacts and sanction-screening features for a regulated financial application (React, TypeScript, React Query), a Material-UI component library in Storybook and the Cypress E2E suite.
  6. Dec 2021 – May 2022

    Web Developer (part-time, in parallel) Nervos Network

    • Contributed to a DAO voting app and built a bridge UI for onboarding to the network.
  7. Jan 2017 – Jul 2020

    Product and CAD engineering Varroc Lighting Systems · Auto Design · Alpha Technology

    Three and a half years in the automotive supply chain: CATIA V5, NX, GD&T, BOM and D-FMEA.

    • Product Engineer, Varroc Lighting Systems (Kraków), Jun 2018 – Jul 2020. Designed front and rear lamp components in CATIA V5: concept, fixing, feasibility, simulation and test results, tooling requests, BOM and GD&T drawings. Worked with the Czech R&D team.
    • CAD Designer, Auto Design (Bielsko-Biała), Sep 2017 – Feb 2018. Designed interior parts (instrument panel, door trim) for Audi and ported parts from CATIA V5 to NX 11.
    • Project Engineer, Alpha Technology, Jan 2017 – Aug 2017. Prepared technical inquiries for the VW Group, worked in the D-FMEA team and trained staff on plastics processes.

05Toolbox

Skills

LLM applications

  • RAG (hybrid BM25 + vector, reranking, citations)
  • Visual RAG over PDFs
  • Agents and tool calling
  • LLM-as-judge
  • Structured extraction
  • Evaluation and benchmarks
  • Prompt engineering

Models and platforms

  • Claude
  • Gemini
  • OpenAI
  • Vercel AI SDK
  • RAGFlow
  • Open WebUI
  • FAISS
  • Microsoft Graph

Languages

  • TypeScript
  • Python
  • Go
  • JavaScript
  • SQL

Backend and infrastructure

  • Node.js
  • Bun
  • Express
  • NestJS
  • FastAPI
  • PostgreSQL
  • Prisma
  • Redis
  • Linux servers
  • GitHub Actions
  • AWS Elastic Beanstalk
  • Telemetry and monitoring

Frontend

  • React
  • Next.js
  • React Native
  • React Query
  • Material-UI
  • Storybook
  • Cypress
  • D3

Engineering and CAD

  • CATIA V5 (advanced)
  • Siemens NX
  • AutoCAD
  • GD&T
  • BOM
  • D-FMEA
  • Plastics
  • OpenCASCADE / build123d
  • STEP and DXF

AI-assisted development

  • Claude Code
  • Codex
  • Agent skills
  • AGENTS.md

Earlier: web3

  • Solidity
  • Foundry
  • ethers.js
  • Cardano

06Proof of work

Commit activity

Every commit across public and private repositories over the last 12 months, refreshed daily by a GitHub Action. Private repos contribute counts and commit titles only.

365-day commit log 2,200+ commits in the last year
Less More

Shipstream

Loading recent commits…

07Background

Education, languages, certificates

Education

  • Silesian University of Technology, GliwiceMSc Eng., Materials Engineering (surface engineering and heat treatment) · 2010–2016
  • TU Bergakademie Freiberg, GermanyExchange, Forming technology (Umformtechnik) · 2014–2015
  • Universidad de Oviedo, SpainExchange, Materials science · 2013

Languages

  • PolishNative
  • EnglishProfessional working (B2)
  • GermanLimited working (B1, DSH-2 certificate)

Certificates

  • CATIA V5, advanced levelCADSOL Design Poland, 2018
  • AutoCAD, levels 1 and 2Autodesk, 2015
  • Generative AI Essentials for Software Developers
  • Algorithmic Trading & Technical Analysis
  • Ethereum 101
  • Blockchain & Bitcoin 101

Awards and publications

  • 2nd place, LearnWeb3 AI Hackathon2023
  • Laser surface treatment technologies: laser ablationCo-author

08For recruiters

Quick facts

Everything a screening call usually asks, in one place.

Target roles
AI Engineer · LLM Engineer · Generative AI Engineer · AI Solutions Engineer · Forward Deployed Engineer · Full-stack Engineer (TypeScript / Python), AI focus
Availability
Available from 1 November 2026, no notice period
Location and mode
Poland · Remote or hybrid, also open to remote roles in the EU and worldwide
Contract
B2B or employment contract
Languages
Polish Native · English B2 · German B1, DSH-2 certificate
Contact
adrian.gora14@gmail.com · LinkedIn

Machine-readable versions

The same profile as files, for applicant tracking systems and AI assistants.

If you are hiring for an AI engineering role, write to me and I will send a short walkthrough of the work that fits it.

Email me