Python Developer / AI / Data Engineer

Python Developer / AI & Data Engineer 💡

Do you want to develop your skills and expertise in an interesting and complex product? You have the opportunity to apply your knowledge and grow in any of the 3 areas described below, or in all of them simultaneously!

Join Aniline.ai! We are a forward-thinking technology company dedicated to harnessing the power of AI across various sectors, including HR, facility monitoring, retail analytics, marketing, and learning support systems. Our mission is to transform data into actionable insights and innovative solutions that empower businesses and professionals to thrive.

We are seeking a highly skilled Python Developer with a strong background in algorithms, data engineering, and cutting-edge AI architectures to join our dynamic team. In this versatile role, you will have the flexibility to work across any combination of three critical areas: Data Pipeline Engineering, AI Stack Development, and Prompt Engineering, allowing you to leverage your diverse expertise and continuously grow your skills.

What You'll Do

You will be a key contributor across our platform, with the ability to focus on, switch between, or work across all of the following core areas based on business needs and your preference:

1. 💾 Data Pipeline Engineering & Processing

• Design, implement, and automate the end-to-end data pipeline for periodic collection, processing, and deployment of results to production.
• Manage the ingestion of raw data (company reviews from various sources) into our GCP Data Lake and subsequent transformation and loading into the GCP Data Warehouse.
• Prepare processed and analyzed data for loading into result tables (including statistics and logs), which serve as the foundation for client reporting on the web portal.
• Develop ETL/ELT processes to generate datasets for updating client-facing databases like Firebase and refreshing reference data in PostgreSQL.
• Automate the pipeline for updating contexts in the Pinecone vector database. This transition from a manual to an automated pipeline is a primary focus.
• Perform general Python development tasks, including maintaining and supporting existing LangChain code for LLM interactions, data processing within Jupyter Notebooks, and developing logging and other auxiliary services.
• Conduct thorough research and analysis of existing infrastructure, data structures, and code bases to ensure seamless integration and stability of new developments.

2. 🤖 AI Stack & Multi-Agent Architecture Development

• Design and implement sophisticated multi-agent architectures for customer communication, marketing, management, and data analytics.
• Develop robust agent communication protocols, distributed AI workflows, task orchestration, agent-based decision-making, and autonomous agent coordination.
• Design and optimize complex LLM interaction architectures (including RAG) to ensure high security and efficiency.
• Tune and optimize LLMs for effective performance using models like LangChain, LangGraph, OpenAI (GPT), Gemini, Claude, Llama, and Mistral.
• Utilize the DS and ML Python Stack (NumPy, Pandas, Hugging Face, OpenAI API).
• Implement development processes using Git, CI/CD, Jenkins, and Docker.
• Work with relational, NoSQL, and especially vector databases for advanced data retrieval.

3. ✍️ Advanced Prompt Engineering & Testing

• Craft and refine effective prompts for LLMs (leveraging the OpenAI API and others) to significantly enhance the quality, relevance, and coherence of generated content across diverse applications.
• Build and maintain a prompt test environment, specifically implemented using Jupyter Notebook, to systematically verify and validate LLM outputs.
• Design and implement Retrieval-Augmented Generation (RAG) architecture, seamlessly utilizing context retrieved from vector databases (e.g., FAISS, Pinecone, or similar) to ground LLM responses.
• Apply strong analytical skills to critically assess and improve LLM outputs.

Requirements

• Proven experience as a Python Developer, with a focus on Data Engineering, AI/ML, or Software Architecture.
• Hands-on experience with cloud-based data infrastructure (GCP highly preferred) including Data Warehouses (e.g., BigQuery) and Data Lakes.
• Experience in designing and automating ETL/ELT data pipelines (e.g., using orchestration tools like Apache Airflow, or similar).
• Familiarity with database technologies, specifically PostgreSQL, Firebase, and vector databases (Pinecone, FAISS, etc.).
• Experience with LLM-based solutions and frameworks like LangChain is highly desirable.
• Proficiency with core Python DS/ML libraries (Pandas, NumPy, Hugging Face).
• Solid grasp of software engineering best practices, including Git, CI/CD, and Docker.

Are you ready to innovate and build the next generation of AI solutions? Apply today!