Backend Engineer - AI & LLM Systems

About the Role

Stallion Group is building technology systems to automate and improve how our businesses

operate.

We are looking for a Backend Engineer with strong AI and LLM experience who can build

the backend infrastructure behind these systems.

You will work on real business problems across our companies, building APIs, data systems,

AI assistants, RAG systems, agentic workflows and business automations.

This is a hands-on engineering role. We are looking for someone who can take a requirement

from an idea to a production-ready system.

What You Will Do

• Design and build scalable backend services and APIs.
• Build backend systems using Python, FastAPI, PostgreSQL, Redis and REST APIs.
• Integrate LLMs such as OpenAI, Anthropic and Gemini into production systems.
• Build RAG systems that allow AI applications to work with company documents and
• internal knowledge.
• Develop AI agents and automated workflows that interact with business systems.
• Build systems where AI can execute tasks while keeping human approval and
• oversight where required.
• Integrate internal applications with third-party APIs and enterprise software.
• Build data ingestion and processing pipelines.
• Work with databases, queues, background jobs and asynchronous services.
• Implement authentication, authorization, logging, monitoring and error handling.
• Deploy and maintain applications on AWS.
• Use Docker, Git and CI/CD to maintain reliable development and deployment processes.
• Write clean, maintainable and well-tested code.
• Work closely with product and business teams to understand problems and turn them
• into working technology.

AI & LLM Responsibilities

You will be expected to have practical experience building applications with modern AI systems.

This includes:

• LLM API integration
• RAG systems
• Embeddings and vector databases
• Document processing and knowledge bases
• AI agents and agentic workflows
• Function/tool calling
• Structured LLM outputs
• Prompt and context management
• LLM evaluation and reliability
• Connecting AI systems to business APIs and databases
• Human-in-the-loop AI systems

You do not need to be an AI researcher. We are looking for someone who knows how to build

reliable AI products and put them into production.

Required Skills

Backend Engineering

• 4–6 years of professional software engineering experience.
• Strong Python experience.
• Strong experience building production backend applications.
• Experience with FastAPI, Django or Flask.
• Strong SQL and PostgreSQL knowledge.
• Experience with Redis and background jobs.
• Good understanding of APIs, authentication and security.
• Experience with Docker.
• Experience deploying applications to AWS or another major cloud platform.
• Understanding of CI/CD and production software development practices.
• Strong Git and software development fundamentals.

AI / LLM

• Hands-on experience building applications using LLMs.
• Experience with OpenAI, Anthropic, Gemini or similar APIs.
• Practical experience building RAG applications.
• Experience with vector databases and embeddings.
• Experience building AI agents or multi-step AI workflows.
• Understanding of tool/function calling.
• Experience connecting AI applications to external systems and APIs.

Good to Have

• LangChain or LlamaIndex
• MCP
• Open-source LLMs
• Local/private AI deployments
• AWS
• Kubernetes
• LLM evaluation and observability
• Enterprise automation
• Experience working with ERP, CRM, accounting or other business systems

What We Expect From You

We are looking for an engineer who can operate independently.

You should be able to take a requirement such as:

“Build an AI system that reads company documents, answers questions, retrieves information

from our business systems and performs certain actions after human approval.”

…and work through the entire engineering problem:

Architecture → Backend → Database → APIs → LLM → RAG → Agents → Integrations →

Testing → Deployment → Monitoring

You should be comfortable making engineering decisions, questioning requirements when

necessary and building systems that can actually be used by the business.

Who This Role Is For

This role is ideal for someone who has spent the last few years building backend systems and

has developed strong hands-on experience with AI and LLM applications.

We are not looking for:

• A pure ML researcher who doesn’t build production software.
• A traditional backend developer with only basic exposure to ChatGPT APIs.
• Someone who has only built demos or notebooks.

We are looking for a strong software engineer who understands modern AI and can build

production-grade AI-powered backend systems.

Why Join Stallion Group?

You will have the opportunity to work on technology that directly impacts real businesses and

operations.

Rather than building isolated prototypes, you will work on production systems, business

automation and AI applications that are deployed across Stallion Group’s businesses.

The role offers significant ownership and exposure across backend engineering, AI, automation, cloud infrastructure and product development.