Python Developer (AI and Data Engineering)

About the Project

We are developing an AI agent for social analytics that will analyze and process data in real-time, automate data collection from social platforms (Telegram, X.com/Twitter, and other sources), and interact with various services.

The candidate will be responsible for building the AI agent from scratch, designing its architecture, training, optimizing, and integrating it into various platforms, as well as automating data collection, processing, and feeding it into the model. This is a product-focused role, where it is essential not only to write code but also to contribute to the design and improvement of the technology.

Position Details

• Work format: Fully remote

• Experience: Minimum 5 years

• Key Technologies: Python, LLM (Large Language Models), API, SQL/NoSQL, LangChain, OpenAI API, Selenium, Scrapy, FastAPI, Kafka, RabbitMQ, Celery

Key Responsibilities

• Developing an AI agent from scratch – designing the architecture, implementing logic, and handling data streams.

• Training, testing, and optimizing the AI agent using LLM (Large Language Models).

• Developing a real-time data pipeline for continuous training and improvement of the model.

• Optimizing model performance – reducing latency, improving response accuracy.

• Developing and fine-tuning neural network models, including pretraining, fine-tuning, and adaptation for specific tasks.

• Integrating the AI agent with external services (Telegram, X.com/Twitter, websites) and building a user-friendly interaction interface.

• Automating data collection and processing, setting up ETL/ELT data pipelines.

• Scraping data from Telegram, X.com (Twitter), and other sources (Selenium, Scrapy, Playwright).

• Interacting with APIs from X.com and Telegram (creating automated accounts, data collection, automation of interactions).

• Working with databases (SQL, NoSQL, vector databases) – designing, optimizing queries, and storing AI-related data.

• Developing APIs and microservices for AI agent interaction (FastAPI, Flask, Django).

Key Requirements

• Strong proficiency in Python + experience with other programming languages (JavaScript, Go, C++ is a plus).

• Deep understanding of neural network architectures and machine learning techniques, including pretraining, fine-tuning, and adaptation of LLMs (OpenAI API, Hugging Face, LangChain, DeepSpeed, PyTorch, TensorFlow).

• Experience working with LLMs – implementation, customization, and optimization of models.

• Experience with API integrations – connecting with X.com, Telegram, and other services.

• Experience with SQL and NoSQL databases (PostgreSQL, MySQL, Redis, MongoDB, Weaviate, FAISS, ChromaDB).

• Experience with ETL/ELT processes and stream data processing (Kafka, RabbitMQ, Celery).

• Experience with web scraping – Selenium, Scrapy, Playwright.

• English proficiency – sufficient for reading and understanding technical documentation.

• Fluent in Ukrainian or Russian.

Additional Technologies (Preferred but Not Required)

• Experience with MLOps – MLflow, Kubeflow, Prefect, Airflow.

• Experience with Kubernetes, Docker, CI/CD (GitHub Actions, GitLab CI/CD, ArgoCD).

• Experience in deploying and fine-tuning LLMs (Fine-tuning, LoRA, DeepSpeed, BitsAndBytes).

• Experience with bots and automation for AI-agent interaction.

• Developing web interfaces and APIs for AI-agent interaction (Streamlit, Gradio).

Soft Skills

• Independence and proactiveness – ability to take responsibility for key development areas.

• Flexibility and adaptability to new technologies – AI and LLM fields evolve rapidly, requiring a quick learning ability.

• Product-oriented mindset – focus on delivering user value, not just writing code.

If you are interested in a challenging and innovative project where you can do more than just coding but actually build a powerful AI agent from the ground up, we would love to hear from you!