SoftwareArrange a call
2014+7 layers14 bricks

AI engineering for teams that answer to auditors

Pilot to production.

Your AI pilot works in the demo. I take it to real users, with a person approving the decisions that matter, answers traced to their source, and runbooks your team can follow without me. Agents I built draft public-tender bids for hundreds of users, and my voice and chat agents have run a quarter of a million live minutes with customers.

Start with a 1–2 week decision sprint →

A 30-minute call, booked through Cal.com.

Seven kinds of software, one row each

Each row of the R is something I’ve built for clients or for my own products, from devices at the base to governance at the top. Scroll to rebuild it row by row.

Step 1: 2016 → 2018

Devices

Firmware for a connected home-security camera: encrypted over-the-air updates, a watchdog that restarts it after a fault, live video, and face recognition that runs on the camera itself.

2 cores

on the camera’s processor ran face recognition, tuned to each household from a short video

2016–2018 · a crowdfunded camera, taken through a full production run

In this row · 2 bricks · 6 parts

  • C/C++ firmware
  • Encrypted OTA
  • Watchdog
  • WebRTC
  • BLE
  • MQTT

Selected work

  • Live video over WebRTC, Bluetooth (BLE) links, and MQTT messaging between camera and cloud

Step 2: 2014 → now

Back-ends

I build the APIs, payment services, queues and databases that products run on, in Go and Java, with automated builds and monitoring.

100,000 users

at peak on a launch platform I built in 3–4 months

2018–2023 · Go back-end · references on request

In this row · 2 bricks · 6 parts

  • Go
  • Java
  • PostgreSQL
  • Queues
  • CI
  • Observability

Selected work

  • A file catalogue that indexed 8.2 million files across 20 drives (ONCE, my own product)
  • A Java payments service on Stripe
  • A gateway that limits how much each API key can call and spend on AI models

Step 3: 2018 → 2023

Ledgers

I built settlement and custody back-ends for banks and digital-asset platforms in Switzerland and Canada, and lending and staking contracts for blockchain products. These systems hold other people’s money, so a bug is a direct loss.

$0 lost

from the contracts and platforms I built

2018–2023 · architect, then VP of Engineering · Go and Solidity · references on request

In this row · 2 bricks · 6 parts

  • Go
  • Solidity
  • Custody
  • Settlement
  • Chain node
  • Bridge

Selected work

  • Lending and staking contracts, a blockchain node and a bridge between chains
  • Security audits of other teams’ contracts
  • Research on detecting and blocking front-running (reordering transactions to take value)

Step 4: 2014 → now

Data

Official records arrive scattered and inconsistent. I bring them into one place, match the same company or person across sources, and link every figure back to where it came from.

14 million

records linked in one graph, each link traced to its source

36 million links between contracts, companies, people and public bodies · Client case 04 →

In this row · 2 bricks · 5 parts

  • Ingestion
  • Entity resolution
  • Graphs
  • Search
  • Provenance

Selected work

  • One procurement platform fed by notices, EU tenders, EU law, the official gazette and complaints-council rulings
  • Company-registry and officials’ declaration records joined to procurement data in one graph

Step 5: 2023 → now

Models

I choose, adapt and serve open models, on your hardware or mine. I have built serving set-ups across the range, from consumer GPUs to workstation cards like the RTX PRO 6000, an NVIDIA DGX Spark and rented H100 servers, each tuned to the model it serves, from small speech models to the largest open models I run for customers. What I ship is tested against fixed evaluation sets, as in client cases 02 and 04.

64 clients

served at once by a 27-billion-parameter model on one desktop-sized DGX Spark, 232 tokens a second in total

speech, search, language, image and video models that I self-host, on consumer, workstation or data-centre GPUs

In this row · 2 bricks · 5 parts

  • Open weights
  • Quantised serving
  • Multi-GPU
  • Evaluation
  • Research

Selected work

  • The largest open models (Kimi K3 class) and smaller ones, served to customers
  • Serving set-ups from consumer GPUs to workstation-grade cards and rented H100 servers, tuned per model and machine
  • Preregistered research on extending a frozen model with a small side network (lab note 01)
  • A stronger model’s review raised a local 27B model from 65 to 74 of 78 real coding tasks, given a second run at twice the benchmark’s time limit (lab note 04)

Step 6: 2024 → now

Agents

I build AI agents that use tools and take actions: voice and chat agents for customers, agents that write documents, and the agents inside a mobile assistant. I build on open agent frameworks such as Pi and LangGraph, or on a custom harness when the product needs tighter control. The voice agents are tuned for low latency and natural conversation, on cloud speech services or fully on premises; the sales agents hand the conversation to a person when it needs one.

60,000+

minutes of live voice and chat in the first 16 days of November 2026, already a record month

250,000+ minutes since launch in May 2026, in English, Romanian, French and many more languages · Client case 02 →

In this row · 2 bricks · 4 parts

  • Orchestration
  • Tools + MCP
  • Real-time voice
  • Human handover

Selected work

  • Voice and chat agents for sales, marketing and legal services, in production
  • Multi-agent pipelines that draft bid documents and other long documents
  • Teal: an iOS and Android assistant whose agents run errands for its users (alpha)
  • Experiments tuning a model to the agent harness that drives it (the DeepSeek harness)
  • 26 small services that AI agents can call and pay for, with checks and receipts anyone can verify (prototype)

Step 7: 2023 → now

Governance

I build the guardrails, audit trails and data policies that let AI run in production. People approve the actions that matter, answers show their source, and budgets and kill switches cap spend. Agents work within set limits, and anything they can’t settle goes to a person instead of going ahead. These controls run in client systems that have been in production for months; the voice agents are having their busiest month yet.

250,000+

minutes of live voice and chat run under per-visitor limits, a daily budget and a kill switch

since May 2026 · every answer marked with its source · Client case 02 →

In this row · 2 bricks · 4 parts

  • Approvals
  • Audit logs
  • Guardrails
  • Fail-closed defaults

Selected work

  • Human sign-off before a drafted document leaves the system (public procurement)
  • No video kept; blurred evidence stills with access logs and a retention limit (camera analytics)
  • Every answer marked with its source, plus per-visitor limits, a daily budget and a kill switch (voice agents)
  • A payment gate for AI agents that only says yes when every check has passed (lab note 02, test build)

Parts list · the whole drawing

Seven layers, devices at the bottom

Read from the bottom up, as on a drawing. Pick an item to go to its step.
ItemLayerYearsFigure
7Governance2023 → now250,000+ minutes of live voice and chat run under per-visitor limits, a daily budget and a kill switch
6Agents2024 → now60,000+ minutes of live voice and chat in the first 16 days of November 2026, already a record month
5Models2023 → now64 clients served at once by a 27-billion-parameter model on one desktop-sized DGX Spark, 232 tokens a second in total
4Data2014 → now14 million records linked in one graph, each link traced to its source
3Ledgers2018 → 2023$0 lost from the contracts and platforms I built
2Back-ends2014 → now100,000 users at peak on a launch platform I built in 3–4 months
1Devices2016 → 20182 cores on the camera’s processor ran face recognition, tuned to each household from a short video

A sample · names withheld

Client work

Four systems I’ve built, described by sector and problem; client names stay private. There are more, and on a call I’ll walk you through the ones closest to your problem.

  1. 01Public procurement · SaaS

    Bid documents drafted by agents, approved by people

    8 kinds of official source, with new procurement notices read every 30 seconds

    Companies bidding for public contracts spend days assembling each tender pack from long, inconsistent documentation, and one missed requirement can disqualify a bid.

    Evidence In production with hundreds of users, and it has passed a legal review.

    Built It reads the official sources, matches each new tender to the companies it suits and drafts the pack in stages: one agent plans it, writers draft the sections in parallel, and an independent reviewer sends weak work back for repair. The system only drafts; a person reviews and submits every document. In a test on real tenders with 17 planted defects, the reviewer agent caught all 17.

    Go · PostgreSQL + pgvector · Kubernetes · Multi-agent pipeline

    On a call Ask for a walkthrough of a pack drafted for a sample company.

    Architecture, back-end and agent design · client system · in production

  2. 02Sales, marketing and legal services

    Multilingual voice and chat agents, live with customers

    250,000+ minutes of live sessions since May 2026, and more than 40,000 sessions in the 60 days to mid-November

    Many customers would rather talk than fill in a form. A voice agent that lags, mishears accents, talks over people or makes up answers is worse than the form, and one left unwatched can run up costs quickly.

    Evidence Live since May 2026 in English, Romanian, French and many other widely spoken languages. Monthly use has grown from about 7,000 minutes in May to more than 60,000 in the first half of November.

    Built Each agent listens and replies in one continuous stream, waits until the caller has finished speaking, and can call tools mid-conversation. The sales agents hand a conversation to a person when it needs one. Answers draw on the client’s documents and, in some deployments, the web, and each one is marked with its source. The deployments limit how many sessions a visitor can open and how many run at once, and have a daily budget, a kill switch and backup models. The agents are tested against fixed sets of conversations.

    LiveKit · Python · ElevenLabs · Retrieval + reranking

    On a call Ask for a live demo, and for the controls that keep cost and answers within bounds.

    Architecture and build · client system · in production

  3. 03Live events and industrial sites · Safety

    Camera analytics that never store video

    0 video recordings kept, checked by an audit command in the client’s deployment

    Event organisers need crowd density and flow in real time. Safety teams need fast alerts when someone is missing protective equipment or goes down. Neither should create a surveillance archive.

    Evidence Piloted on site at a large music festival in Romania with the organisers and public authorities, and now going into production for an industrial client. One machine analyses 16 live camera streams.

    Built Live streams are analysed in memory on a GPU: crowd counts, flows and alerts for events, and protective-equipment and person-down alerts for industrial sites, shown on a bilingual operator console. No video is recorded. An audit command, run in the client’s deployment, fails if it finds a video file, an unblurred image or an image with no database record behind it. Where evidence is needed, only blurred stills are stored; every access to them is logged, and they are deleted after a fixed period.

    Computer vision · TensorRT · Python · TypeScript

    On a call Watch me run the no-video audit live, and ask for a demo.

    Architecture and build · client system · from on-site pilot to production

  4. 04Public records · Romania

    Romania’s public records, linked and traced to source

    14 million records in one graph, with 36 million links between contracts, companies, people and public bodies

    Procurement, company-registry and officials’ declaration records are public, but split across systems and too large to search by hand. An investigation needs every link traced to its source.

    Evidence Runs on Romanian procurement, company-registry and declaration data: 6.4 million contracts and 4.1 million companies so far, imported at more than 10,000 rows a second. Every change to the agent must pass a fixed set of 16 cases before it ships.

    Built One graph joined from the three sources, every link carrying its source. An agent with 12 tools answers questions by searching the graph, building views on demand and pulling out the records it needs. The agent and the extraction models run on premises, on a GPU server. The agent reaches the data only through a gateway that decides which queries it may run.

    Python · PostgreSQL · Neo4j · Self-hosted LLM

    On a call Ask for a demo on Romanian procurement data.

    Architecture and build · part client work, part own research

Work with me

Ways to work together

Start with a short sprint, take one system to production, or keep me on for the long term. I lead every engagement myself; when the work needs a bigger team, I bring in senior engineers I have worked with before.

  1. 1–2 weeks

    Decision sprint

    Before you commit budget to an AI system.

    A written, sourced answer: architecture, risks, a cost range and a recommended next step. That may be to build, to buy or to stop. Presented on a call.

    It covers one question about one system, with read access to what exists and no changes in production.

    Fixed price, agreed after the first call.

  2. 4–12 weeks per phase

    Build to production

    After a sprint, or when the spec is already clear.

    One bounded workflow taken to production: code, tests, evaluation, logging and human oversight, runbooks and a handover session.

    Acceptance criteria and exclusions are agreed in writing before work starts. Larger systems are built in phases, and a support window follows each handover.

    Fixed price per scope, paid in milestones.

  3. Open-ended, monthly

    Long-term partner

    When you want the same people owning your AI systems over time.

    Fractional CTO work, continued development and support for the systems we built, or a standing team for a larger roadmap: strategy, architecture decisions in writing, vendor and model choices, governance.

    A three-month start, then month to month for as long as it’s useful. Time and team size go up or down as the work changes.

    Monthly fee, set by the time and team you need.

The practical details

Who you work with
Me, directly. On larger builds, engineers from my own network, always named in the contract.
Where
Remote from Cluj-Napoca, on Eastern European Time. On site for kick-off, key reviews and handover.
Pricing
There is no price list; the scope sets the cost. A fixed price or a monthly fee, agreed in writing. A sprint can turn into a build, and a build into a long-term engagement.
Your data
You decide where it goes, in writing: EU-only providers, the major US model providers under business terms, or models on your own hardware. I build the controls that GDPR and the EU AI Act expect, such as human oversight, logging, data minimisation and fixed retention, and document them for your compliance review.
Invoicing
REDCOM SOFTWARE SRL, an EU company. VAT RO38869281. EUR or USD.
References
Available after a first conversation, with the client’s consent.

Own products

Products I build and run

I build products to try methods before I use them for clients, and run them on my own servers. My monitoring has watched 18 projects for months, with read-only access. Provinciae is open to everyone; the others are in private use or beta.

History

Since 2014

  1. 2014 → 2016

    Engineering

    I started as a back-end engineer, building data systems in Java and C++.

  2. 2016 → 2018

    Devices & IoT

    Firmware for a crowdfunded home-security camera, from prototype through a full production run: encrypted updates, live video, and face recognition running on the camera itself.

  3. 2018 → 2023

    Leadership & fintech

    I founded Redcom Software in 2018. Since then I have been CTO twice, VP of Engineering (2021–2023) and technical architect four times, and co-founded two companies. Most of that work was settlement, custody and ledger back-ends for banks and digital-asset platforms in Switzerland and Canada, where no funds were ever lost on a system I built.

  4. 2023 → now

    AI for clients

    Voice and chat agents with more than 250,000 live minutes, bid-drafting agents used by hundreds of people, a public-records graph of 14 million records and camera analytics that keep no video, for clients in Europe and the Middle East. Alongside them, my own products and research.

Own research · 4 notes

Lab notes

Research I run alongside client work, on local models, agents and evaluation. Each note gives the method and the numbers, including the results that went against me.

Arrange a call

Thirty minutes, no slides. Tell me what the system has to do and what it must not get wrong, and I’ll tell you whether I’m the right person to build it.

Booked through Cal.com.