Junior Applied AI Engineer

About SynthEngine

SynthEngine is building a data-backed AI platform that uses synthetic populations to explore how people may think, make decisions, interact, and respond to changing real-world scenarios.

The platform combines government and survey data, structured representations of people and their environments, quantitative decision models, and AI-powered reasoning and interaction systems.

We are looking for a hands-on engineer to help turn our existing prototype into a more reliable, integrated, and testable product.

What you will work on

1\. Build and improve the core platform

Work with an existing Python-based codebase, understand its architecture, trace how data moves through the system, and resolve bugs and integration issues.

2\. Connect AI and simulation components

Help integrate the synthetic population, quantitative decision engine, scenario processing, and AI reasoning components so that they work together consistently.

3\. Work with structured data

Build and improve data-processing pipelines for demographic, economic, survey, and other structured datasets. Maintain data quality, source attribution, and clear documentation.

4\. Develop and integrate AI capabilities

Work with LLM APIs and AI-agent workflows where appropriate. Help implement structured inputs and outputs, context retrieval, scenario reasoning, and controlled interactions between simulation components.

5\. Test and validate behaviour

Write automated tests, reproduce bugs, compare simulation runs, check that changes do not break existing functionality, and help build repeatable evaluation workflows.

6\. Make the system easier to operate

Improve APIs, error handling, logging, documentation, and development workflows so that the product becomes easier to maintain and extend.

7\. Use AI coding tools responsibly

Use AI-assisted development tools to work efficiently, while understanding, testing, and verifying the code you produce.

Required skills

• Good working knowledge of Python.
• Ability to read, understand, debug, and modify an existing codebase.
• Familiarity with APIs, JSON, data structures, and databases.
• Basic understanding of software testing, Git, and version control.
• Ability to break complex problems into smaller, testable tasks.
• Willingness to learn unfamiliar technical concepts and document your work.
• A practical project portfolio demonstrating that you can build working software.

Good to have

• Experience with FastAPI, Flask, Django, or similar backend frameworks.
• Experience integrating LLM APIs or building AI-powered applications.
• Exposure to multi-agent systems, knowledge graphs, data pipelines, or simulation.
• Familiarity with PostgreSQL, Docker, automated testing, or cloud deployment.
• Experience using AI coding assistants to develop and debug real applications.

You do not need to have experience in every preferred area. Strong Python fundamentals, sound engineering habits, and the ability to learn are more important.

What success looks like

First 30 days: Understand the architecture, establish a reliable local development environment, run the available tests, and document the main execution paths and known issues.

First 60 days: Fix agreed integration gaps and deliver a working, testable scenario workflow with reproducible results.

First 90 days: Deliver a documented end-to-end simulation workflow, a reliable regression test suite, and a clear report of what works, what remains incomplete, and what needs further research.

Who should apply?

We welcome early-career engineers and recent graduates with strong practical projects. We value curiosity, disciplined debugging, honest technical judgment, and the ability to explain complicated problems clearly.

Please share your resume, GitHub profile or project portfolio, and a short explanation of a technical project you personally built.

*Important *

: This is a hands-on engineering role. It is not a prompt-writing position, a data-entry role, or a requirement to train a large language model from scratch.