Python AI Engineer

We are seeking an experienced Python AI Engineer to develop and optimize systems interacting with large language models (LLMs), including chatbots, agent systems, and Retrieval-Augmented Generation (RAG) architectures. You will work on building high-performance, scalable solutions integrated with cloud platforms and modern AI tools, ensuring rapid development pace and high code quality. The role involves both independent work and collaboration within cross-functional teams.

Requirements:

• 3+ years of Python development experience and 2+ years with FastAPI or Django;
• Proficient in Python asynchronous programming;
• Hands-on experience with LLMs (OpenAI API, GPT-4/4o, Grok);
• Knowledge of RAG, prompt engineering, and understanding of model fine-tuning processes;
• Experience with NLP libraries (e.g., LangChain);
• Experience with Docker, Kubernetes, and containerization;
• Knowledge of databases: PostgreSQL, MongoDB, vector databases (pgvector, e.g., ChromaDB, FAISS);
• Experience with cloud platforms: AWS (DynamoDB, EC2, S3, Lambda), Azure, Supabase;
• Proficiency in Git, GitLab CI/CD, or Azure DevOps for version control and automation;
• English: B1+/B2 level (confident communication with technical and non-technical teams);
• Analytical thinking, attention to detail, and ability to work under uncertainty;
• Ability to quickly master new technologies and tools.

Responsibilities:

• Develop and optimize backend systems using Python and FastAPI to create APIs integrated with LLMs (OpenAI API, GPT-4/4o, Grok, YandexGPT);
• Design and implement RAG pipelines for data processing, vectorization, and response generation using libraries like LangChain, LangGraph, CrewAI, or Autogen;
• Create and maintain NLP-based chatbots, ensuring high accuracy and performance;
• Develop agent systems for text analysis, multimedia generation (audio, video, avatars), and automated decision-making processes;
• Integrate with cloud platforms (AWS, Azure, Supabase) and utilize serverless/microservices architectures;
• Work with vector databases (ChromaDB/FAISS/Pinecone/PostgreSQL+pgvector) for semantic search and data processing;
• Configure CI/CD pipelines using Azure DevOps, GitLab CI/CD, or similar tools;
• Ensure code quality through reviews and testing;
• Participate in fine-tuning LLMs, prompt engineering, and model optimization for specific tasks (e.g., text summarization within character limits).

Nice to Have:

• Experience with local LLMs and their inference;
• Frontend technology knowledge (React, Next.js, TypeScript) for full-stack tasks;
• Experience with WebSocket, Socket.IO, or WebRTC for real-time communication;
• Knowledge of MLOps/LLMOps (MLflow, Kubeflow) and vLLM;
• Experience with Celery, Redis, Kafka for asynchronous tasks and caching;
• Knowledge of Terraform, Pulumi, or AWS CDK for infrastructure automation;
• Experience with multimedia (audio/video processing, avatars, STT/TTS).

We look forward to sharing more about the company when you meet us!