Backend Engineer - AI and Large Language Model Systems

About the Role

Stallion Group is advancing technology systems aimed at automating and enhancing the operations of its companies. We seek a Backend Engineer skilled in AI and large language model (LLM) technologies to develop the backend infrastructure supporting these initiatives.

You will tackle practical business challenges across our enterprises by creating APIs, data systems, AI assistants, retrieval-augmented generation (RAG) systems, agentic workflows, and business automations. This role requires hands-on engineering expertise to translate concepts into fully operational production systems.

Key Responsibilities

• Architect and develop scalable backend services and APIs.
• Construct backend components using Python, FastAPI, PostgreSQL, Redis, and RESTful APIs.
• Integrate LLM platforms such as OpenAI, Anthropic, and Gemini into enterprise-grade solutions.
• Create RAG systems enabling AI solutions to process company documentation and internal knowledge.
• Design AI agents and automated workflows that interact with business applications.
• Implement systems allowing AI to perform tasks with necessary human oversight and approval.
• Incorporate enterprise applications with third-party APIs and software.
• Build data ingestion pipelines and processing systems.
• Manage databases, queues, asynchronous services, and background jobs.
• Implement robust authentication, authorization, logging, monitoring, and error management.
• Deploy and sustain applications on Amazon Web Services (AWS).
• Utilize Docker, Git, and CI/CD practices for reliable software development and deployment.
• Produce clean, maintainable, and well-tested source code.
• Collaborate closely with product and business teams to translate needs into effective technology solutions.

AI & LLM Specific Responsibilities

• Integrate LLM APIs effectively.
• Develop RAG-based applications.
• Utilize embeddings and vector databases.
• Process documents and manage knowledge bases for AI use.
• Build AI agents and workflows involving multiple step interactions.
• Implement function or tool calling within AI systems.
• Manage prompt engineering and context for LLM tasks.
• Conduct evaluation and reliability analysis of LLM outputs.
• Connect AI systems with business APIs and data stores.
• Design human-in-the-loop AI frameworks.

Candidate Profile and Requirements

• Bachelor's degree or equivalent experience is implied but not explicitly stated.
• 4 to 6 years of professional experience in software engineering focused on backend development.
• Proficient in Python programming.
• Experienced in building production-ready backend applications using frameworks such as FastAPI, Django, or Flask.
• Strong skills in SQL and extensive PostgreSQL knowledge.
• Hands-on experience with Redis and managing background job systems.
• Solid understanding of API development, authentication methods, and security best practices.
• Experienced with containerization using Docker.
• Familiarity with deploying applications on AWS or comparable cloud platforms.
• Knowledge of CI/CD pipelines and production development workflows.
• Strong command of Git and core software development principles.
• Demonstrated practical experience building AI-powered applications that utilize LLMs such as OpenAI, Anthropic, or Gemini APIs.
• Experience with RAG applications and vector database technologies.
• Proven background in developing AI agents and multi-step AI workflows.
• Understanding of function/tool calling within AI contexts.
• Experience integrating AI with external APIs and enterprise systems.

Additional Preferred Skills

• Working knowledge of LangChain or LlamaIndex frameworks.
• Familiarity with Microsoft Certified Professional (MCP) credentials.
• Experience with open-source LLMs.
• Deployment of local or private AI environments.
• Knowledge of Kubernetes infrastructure.
• Expertise in LLM evaluation and monitoring techniques.
• Exposure to enterprise automation solutions.
• Experience with ERP, CRM, accounting, or other business software systems.

Expectations From the Engineer

We seek a self-driven engineer capable of independently managing requirements such as building AI systems that read business documents, answer queries, retrieve data from internal systems, and perform actions under human supervision. The engineer should confidently navigate the end-to-end engineering cycle from architectural design to deployment and monitoring.

The candidate must be comfortable making technical decisions, challenge requirements when necessary, and deliver business-ready solutions effectively.

Who Should Apply

This role fits professionals with several years of backend engineering experience coupled with substantial hands-on AI and LLM application expertise. We are not seeking ML researchers without product software development experience, general backend developers with minimal AI exposure, or candidates who have only worked on demos or experimental prototypes.

Why Join Stallion Group?

This position offers the opportunity to build impactful, production-level AI and automation technologies used across real-world businesses. The role includes significant responsibility and participation in backend engineering, AI innovation, cloud infrastructure, and product advancement.