SEEKING WORK | Senior Django/Python Web-developer & AI Engineer - Platform, Architecture, Ops, Applied AI
Location: Thailand (UTC+7)
Remote: Yes, and available for hybrid arrangements in Thailand.
Technologies: Django, Python, PostgreSQL, Redis, Celery, HTMX, Tailwind, Docker, APIs, RAG/MCP
Resume/CV: https://edwin.genego.io/about
Email: edwin@genego.io
Senior full-stack Django/Python engineer for founders and lean teams that need platform, product, architecture, and ops ownership. Django has been my daily driver since 2018. I build production web platforms, MCPs, APIs, integrations, internal tools, document/data automation, and AI-enabled workflows. Recent R&D: generative image/video pipelines, Lora training, multi-model orchestration, prompt architecture, and repeatable creative AI tooling—but the broader pattern is platform engineering.
Open to fractional or project-based work, especially 2-6 week focused cycles with startup founders, cofounders, agencies, or product teams. Next to client work, for the past 2 years I have been busy building and experimenting with agent harness systems (before it was cool) and Gen AI video automation, orchestration and model training. You can read about that here: https://edwin.genego.io/blog - https://edwin.genego.io/projects
Why does Railway deserve any blame here at all? It was an MCP with elevated infra access, that the user willingly connected through Cursor, which allowed an LLM Agent to manage infra on Railway. The user would first have gone through oAuth confirming the access level scope (I would have rejected the moment it indicates to me that it can delete critical infra and backups...). So obviously it has access to all commands the user would also have access to. From my perspective the blame is entirely on the user, and partly on Cursor for not enforcing HITL correctly across their agents.
Putting AI aside, people make mistakes. One of the most common mistakes people make is deleting the wrong thing. After they realize the mistake, people want to restore the thing they deleted from backups. Thus deleting the thing and deleting the backups of the thing should always be separate operations.
Senior full-stack Django/Python engineer for founders and lean teams that need platform, product, architecture, and ops ownership. Django has been my daily driver since 2018 — I've only worked with Django-native startups. I know the framework deeply: ORM, migrations, admin, middleware, signals, async, deployment. I build production web platforms, APIs, integrations, internal tools, document/data automation, and AI-enabled workflows. Recent R&D: generative image/video pipelines, Lora training, multi-model orchestration, prompt architecture, and repeatable creative AI tooling—but the broader pattern is platform engineering.
Open to fractional or project-based work, especially 2-6 week focused cycles with startup founders, cofounders, agencies, or product teams.
I keep having this conversation with clients. If you want to allow an LLM to delete, create or update data; you need to do this with a human in the loop, and explicit hitl gating against execution; where the agent can't even call the tool without triggering an update on the UI that has to be confirmed (then the confirmation issues the actual tool call).
I am a well-seasoned software engineer; who grew up with a hackers mindset. I am currently exploring create AI tooling around image & video generation pipelines, multi-model orchestration, prompt engineering systems and cost-optimized workflows. I am currently looking for a startup or agency interested in working with me; as I have availability coming up in the next few months. I have 10-Years of experience (full-stack) mostly with Django, Python & Tailwind. I have most of my work outlined on my website.
Sr. Software Engineer building production Django apps with practical AI integration. I specialize in creative AI tooling , image generation pipelines, multi-model orchestration (Flux, SDXL), prompt engineering systems, and cost-optimized workflows. Current work: 20+ custom management commands for AI image generation, character IP systems, scene replication with layered prompt architecture. I help teams ship AI-powered creative tools without risky rewrites, handling multi-model workflows, resume-capable operations, and obsessive cost tracking. Looking for fractional or project work (2-6 week cycles) involving generative AI, creative tooling, or content pipelines.
Whenever I saw people complain about LLMs writing code, I never really understood why they were so adamant that it just didn’t work at all for them.
The moment I did try to use LLMs outside of Django, it became clear that some frameworks are just much easier to work with LLMs than others. I immediately understood their frustrations.
LLM is the fad of the day, and these sort of articles provoke the natural get-rich-quick-greed inherent in all of us, especially the young tech-types. As such they are clickbait, and also a barometer of the silliness that is widespread.
I am curious why re-reading incerto sharpens your bullshit sense. I have read a few in that series, but didnt see it as sharpening my bullshit sensor.
Django has been one of the biggest reasons why web development has been so enjoyable to me. Whenever I switched to something else, I just felt too spoiled by everything that Django gives you. So I always ended up back with Django, and have no regrets at all specializing deep down that path.
Have you tried Ruby on Rails. That's my experience with Rails. Everytime I've tried something else (for web dev), I just felt too spoiled with Ruby & Rails and went back. This includes Django and Phoenix (Elixir).
Edit: The only thing that Rails lacks is a decent Admin UI included as part of Rails. I know that there are some external gems that can be used, yet that's something that should be part of the framework in my opinion.
Even before you get to the lacking Admin UI, the first thing Rails asks me to do is implement authentication. Coming from a true batteries-included framework like Django that feels like a complete non-starter.
I use Django a lot and it's great, but even I have to admit that Ruby on Rails is better. It's just that I don't really do a lot of Ruby, so I ended up on the familiar tech stack, and also finding other developers to join a project is much easier with Python.
I feel very comfortable with Django on the frontend, what are you missing there? I usually use Tailwind or Bulma, with HTMX and AlpineJs. I feel like the experience can be very much React like, even if you leave out HTMX. The frontend game of Django really changed about 2 years ago (at least for me).
Laravel's Blade templates are just absolutely phenomenal. The partial rendering, the integration with Livewire, the first class component paradigm. It's just far beyond stock Django / Jinja at this point and delivers some serious dev experience performance boosts.
Glad to hear that works for you. But nothing of what you are mentioning is part of Django, nor an official package,etc.
And I’m not going to get into the details of whether that stack would work for non backend developers, developers working on medium/large projects and/or medium/large teams. That’s a separate and unrelated discussion.
But compare what Django brings you (Stone Age templating system and that’s it) to what Laravel provides out of the box (or via official packages) like assets bundling, live reloading, an amazing and modern template system with proper “component like” partials or even if you need them, the “big guns” such as Inertia or Livewire. More or less the same is true for Rails with the Hotwire stuff.
There’s absolutely no point of comparison here. Even if that works for you, Django is not even in the same league.
It is still a great backend framework though, which was my point.
I am a SR. SWE building production systems and workflows with GenAI. I am currently specializing down the road of creating digital characters and universes through diffusion models (both video as well as images). On my blog (https://edwin.genego.io) you will find extensive case study material on the topic, as well as a showcase of my own creative skills. Keep in mind that I come to this through the lense of applied-GenAI and not a pure AI/ML background; although I have worked with AI/ML teams well before 2022.
I am currently looking for a startup, company, agency or anyone really that is doing world, universe or character building with AI. Whether this is through GenAI models by building IP or something else. my current work spreads 50+ custom management commands for AI image generation, character IP systems, scene replication with layered prompt architecture; which is more or less openly documented on my website. What I am also looking for is fractional or project work (2-6 week cycles) involving generative AI, creative tooling, or content pipelines. https://edwin.genego.io/blog
Open to fractional or project-based work, especially 2-6 week focused cycles with startup founders, cofounders, agencies, or product teams. Next to client work, for the past 2 years I have been busy building and experimenting with agent harness systems (before it was cool) and Gen AI video automation, orchestration and model training. You can read about that here: https://edwin.genego.io/blog - https://edwin.genego.io/projects
reply