Python Backend Engineer (AI Agents & SaaS Integrations)

Gramian Consulting Group · Mexico · $78K/yr

IT Services and IT Consulting · 2-10 employees

9 h ago

Remote Mid (2-5 yrs) Contractor Mexico

About the role

Develop and maintain Python backend applications, REST APIs, and SaaS integrations to support autonomous AI agent training. Create and validate complex software tasks and evaluation rubrics to ensure realistic AI performance.

What they look for

Python Docker Backend Development FastAPI Flask Django REST APIs Microservices Git Claude Code Software Testing Integration Validation SaaS Integrations AI Coding Assistants Workflow Automation

Requirements

Requires at least 3 years of professional software engineering experience with strong proficiency in Python and backend frameworks. Candidates must have hands-on experience with Docker, Git, and AI coding tools like Claude Code.

Full description

About Us

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

Role Overview

Our client is supporting the development of advanced AI systems by creating the software environments, workflows, and evaluation data required to train and assess autonomous AI agents.

We are looking for experienced Python Backend Engineers to develop realistic backend applications, SaaS integrations, and complex software tasks. Depending on the assigned track, engineers will either build full-service backend environments and connectors or create and validate long-horizon AI tasks and evaluation criteria. Strong experience with Python, Docker, backend development, and AI coding tools—particularly Claude Code—is essential.

CONTRACT: Freelance contractor, paid per approved task

COMMITMENT: Minimum of 1 completed and approved task per day

LOCATIONS: Remote

PROCESS: Short screening followed by a technical evaluation (Python, Docker)

NOTES: Payment is $300 per approved task. The engagement is expected to last 2–3 weeks, with an immediate start.

Responsibilities:

Build Python backend applications that replicate the functionality of established SaaS platforms.
Develop REST APIs, microservices, integrations, and complete backend workflows.
Build new SaaS connectors from scratch and adapt existing integrations when required.
Perform comprehensive backend testing and integration validation.
Verify that connectors accurately reproduce the behavior of the systems they emulate.
Analyze software workflows and datasets to identify realistic long-horizon AI tasks.
Create representative tasks based on real-world tools, processes, and user interactions.
Conduct structured QA to validate task accuracy, realism, and completeness.
Write clear evaluation rubrics covering correct, partially correct, and insufficient outcomes.
Use Claude Code and other AI coding agents throughout development, testing, and validation.

At least 3 years of professional software engineering experience.
Strong proficiency in Python and backend frameworks such as FastAPI, Flask, or Django.
Proven experience building backend applications, REST APIs, or microservices.
Hands-on experience with Docker, Git, and basic software delivery pipelines.
Strong practical proficiency with Claude or Claude Code.
Experience using AI coding assistants as part of daily software development.
Professional written and spoken English.
Strong knowledge of software testing, version control, and code-quality practices.