Webmagic

We’re Expanding and Looking for Talented Developers!

You’ll work directly with our technical founder (experienced developer with a strong AI interest), helping shape our AI direction from the ground up.

The main focus is prompt engineering, the ability to build pipelines for AI agents, and working with memory and external data.

Our team specializes in working with startups, starting from the earliest stages of their development. Each project we take on is a unique challenge, requiring innovative and effective solutions. That’s why we always stay at the cutting edge of technology.

We believe that productive work is only possible in a comfortable environment with excellent planning. The best solutions are built on well-thought-out architecture, quality code, and modern technologies.

If these priorities resonate with you, you’ll love being part of our team!

Requirements

• 1+ years of experience with LLM APIs (e.g., OpenAI, Hugging Face Inference API).
• Understanding of how pretrained models work (LLMs, image-to-text, TTS/STT).
• 1+ years of experience building simple pipelines in Python using libraries like Transformers, Diffusers, Gradio, LangChain, or similar.
• 1+ years of experience with visual AI tools (ComfyUI, Automatic1111, or similar).
• Understanding of REST APIs and integrating ML features into web services (via API requests).

• Ability to work with texts: translations, basic transformations (tokenization, embeddings, chunking, etc.).

   

Nice-to-Haves

• 1+ years of experience with or interest in RAG (Retrieval-Augmented Generation).
• Basic fine-tuning skills or familiarity with LoRA / DreamBooth.
• 1+ years of experience building simple chatbots or AI agents.
• Exposure to multimodal tasks (text → image / audio / video).
• Prompt engineering knowledge to control LLM behavior.

• 1+ years of experience preparing glossaries or structured files to support translation tasks.

   

Responsibilities

• Help build and maintain simple AI pipelines for use in our internal tools and client web services.
• Integrate LLM and multimodal models (image, video, audio) into production-ready features.
• You’ll work directly with our technical founder (experienced developer with a strong AI interest), helping shape our AI direction from the ground up.
• Collaborate with backend/frontend engineers to deliver AI-driven features. Prepare and use glossaries, structured data, and RAG files for translation and document understanding tasks.
• Build early versions of AI-powered chatbots, assistants, and user-facing agents.

• Use both Python and visual tools (e.g., ComfyUI) for building and debugging pipelines. Take initiative and learn new tools or techniques as needed — you’ll be our first AI specialist.

   

Additionally:

• DevOps support is available in the team to help with deployment and running models locally.

• Complex integrations or tuning tasks can be delegated internally if needed.

   

What We Offer

• Possibility to be a part of startups from around the world
• Supportive, understanding, and flexible management
• Paid vacations and sick leave
• A friendly and welcoming team