Python Backend Developer (RAG)

Authority Partners; Ciudad de México; Híbrido; MXN 951,000 - 1,298,000; Jornada completa

Descripción de la vacante

A leading global IT services company seeks a skilled Python Backend Developer to build a Retrieval-Augmented Generation (RAG) chat application. This role focuses on custom development of high-performance systems, including API architecture and AI logic implementation. Ideal candidates must have advanced Python skills and experience in asynchronous programming. The company offers a competitive remuneration package and opportunities for collaborative learning and career growth.

Servicios

Cutting-edge technologies

Collaborative learning environment

Career growth opportunities

Mentorship programs

Formación

• Advanced proficiency in Python (3.10+) with asynchronous programming experience.
• Strong understanding of LLMs and semantic search mechanics.
• Experience in designing clean and maintainable REST APIs.

Responsabilidades

• Build and optimize the end-to-end RAG pipeline.
• Develop high-concurrency asynchronous RESTful APIs.
• Integrate and optimize vector databases for high-precision retrieval.

Conocimientos

Python expertise

Asynchronous programming

API design

Database design

Knowledge of Large Language Models (LLMs)

Educación

Bachelor's degree in Computer Science or related field

Herramientas

FastAPI

Flask

PostgreSQL

Docker

Descripción del empleo

We are looking for a Python Backend Developer to build a custom Retrieval-Augmented Generation (RAG) chat application. Our goal is to build a lean, high-performance system from the ground up, focusing on custom logic for data retrieval and AI orchestration rather than relying on heavy third-party frameworks.

Key Responsibilities

• Custom RAG Development: Build the end-to-end RAG pipeline, including custom document parsing, text chunking strategies, and context injection logic.
• API Architecture: Develop and scale high-concurrency, asynchronous RESTful APIs using FastAPI (preferred) or Flask.
• Vector Search Implementation: Integrate and optimize vector databases (e.g., pgvector, Pinecone, or Weaviate) to ensure high-precision retrieval for AI grounding.
• Core AI Logic: Implement memory management, window handling, and custom prompt engineering natively in Python.
• System Performance: Optimize the latency of the "Retrieve-then-Generate" loop to provide a seamless user experience.

Technical Requirements

• Python Expertise: Advanced proficiency in Python (3.10+), with deep experience in asynchronous programming (asyncio) and building production-grade backends.
• AI/RAG Fundamentals: A strong understanding of Large Language Models (LLMs), embeddings, and the mechanics of semantic search.
• "Framework-Free" Philosophy: Ability to implement complex LLM patterns (like history management and data grounding) using native Python code rather than wrappers like LangChain or LlamaIndex.
• Database Design: Experience with SQL (PostgreSQL) and a solid understanding of how to handle vector data at scale.
• API Mastery: Proven track record of designing clean, maintainable, and well-documented REST APIs.

Nice to Have (Preferred Skills)

• AWS Ecosystem: Experience with Amazon Bedrock and related services (S3, Lambda).
• Cloud Infrastructure: Familiarity with deploying applications on AWS or using Infrastructure as Code (Terraform/CDK).
• DevOps: Experience with Docker, CI/CD pipelines, and container orchestration.
• Monitoring: Knowledge of tools for tracking LLM performance, latency, and response quality.

Education

• Bachelor's degree in Computer Science, Software Engineering or related field would be of great value, but if you’re passionate and have the experience that backs up your abilities, for us, talent outweighs degree every time.

AP Perks

• Most cutting-edge technologies
• Opportunity to work with people who are at the top of their field
• Great culture and environment
• Competitive remuneration package. We reward excellence
• Career growth
• Collaborative learning environment
• Mentorship programs
• Professional training

About Authority Partners

Authority Partners is a leading global IT services company with over 25 years of experience, serving clients within the financial, healthcare, insurance, mortgage, and technology sectors among many others. We are committed to building relationships with IT professionals who possess integrity, dedication, teamwork, and the desire to learn and grow with us. We specialize in placement for long-term contract and permanent opportunities and helping our consultants achieve their career success.

Authority Partners is an equal opportunity employer and is committed to providing a workplace that is free from all types of discrimination, as well as from abusive or offensive behavior and harassment.