Python Backend Developer (AI)

We’re looking for a Python Backend Developer (AI) — an engineer who knows how to turn neural networks into real, working product features: launching, adapting, and optimizing models, and integrating them into a production-ready system.

What we’re building

We’re creating the AI IDE of the future — an intelligent environment for developers and AI enthusiasts across desktop, mobile, and web. It’s a place where you can build not just code, but also images, audio, video, and design — powered by cutting-edge LLM agents.

This is an AI startup inside a stable product company, right at the exciting early stage. We’ve already built our MVP, are testing before release, and have real users and a strong team of engineers on board.

Our product uses advanced AI models and technologies, including:

- The latest LLMs.

- Modern AI tools like RAG, LangChain, LoRA, and more.

- Various model types — image, video, audio, etc.

- AI agents and pipelines.

We work in the GMT+3 time zone (team daily meetings are at 12:00 pm).

Tasks

• Developing the backend of an AI IDE, responsible for integrating LLM models into the product.

• Building RAG components and pipelines using LangChain, LlamaIndex.

• Deploying, configuring, and optimizing large language models (LLMs) — both cloud-based and local.

• Designing and maintaining REST/gRPC APIs for interaction with AI modules.

• Integrating multimodal models (via API and locally).

• Working with image, video, and audio generation using Flux, Qwen, OpenAI, Google, Sora, Kling, Suno, and others.

• Building services for context, prompt, and request management for AI models.

• Building next-generation AI features for smart code generation and seamless autocompletion.

• Optimizing the performance, scalability, and stability of AI features.

• Owning technical tasks end-to-end — from concept to release and maintenance.

• Collaborating closely with AI engineers to turn ideas into production features.

Requirements

• 3+ years of experience in Python backend development.

• 2+ years working with AI tools (RAG, LangChain).

• Hands-on experience building intelligent pipelines and agents — LangChain, LlamaIndex, Autogen, or your own solutions.

• Experience integrating models into production features (via APIs, OpenAI, Claude, etc.).

• Understanding of LLM architecture and experience using models via API/SDK.

• Solid skills in designing microservices and REST/gRPC APIs.

• Experience with multimodal systems — generating/processing images, video, and sound.

• Strong database knowledge (PostgreSQL, Redis).

• Experience with Docker, Kubernetes, CI/CD.

• Independence, clean code, and the ability to deliver features fast and reliably.

• A genuine passion for AI and startups.

• Fluent Russian, English B1.

Nice to have

• Hands-on experience with LLM.

• Prompt engineering background.

• Advanced LangChain scenarios.

• Experience working with vector databases.

We offer

• Full-time remote work (External Vendor contract).

• Competitive compensation (EUR, USD, or crypto).

• Flexible working hours.

• The opportunity to show creativity, generate ideas, and directly influence the architecture of the AI product.

• Access to cutting-edge AI tools and platforms.

• A team of professionals specializing in AI.

• Positive and friendly atmosphere.