AI Engineer (LLMs + C#)

Job Description   Join Aperia Solutions, a leader in SaaS solutions for the Payments and Compliance industries. Aperia is a Texas-based fintech and managed consultancy firm that creates custom SaaS applications and other software-based solutions for the payments, banking, and processing industry. Founded in 1999, Aperia offers business intelligence, risk management, compliance, and customer intelligence platforms. With offices in Dallas, Washington DC, and Vietnam, Aperia is a fast-paced, global organization that strives to improve efficiency in compliance, risk, and customer service operations. Aperia’s clients include banks, processors, payment facilitators, merchant service providers, independent sales organizations, and government entities. A career at Aperia promises a great challenge, culture, and opportunities to forge your own path.   We are seeking an experienced  AI/LLM Software Engineer  to join our growing development team and help design, build, and integrate intelligent solutions into modern enterprise applications.   The ideal candidate has hands-on experience working with  Generative AI, Large Language Models (LLMs), AI-assisted software development, and AI-powered applications . You will work closely with software engineers, architects, business stakeholders, and product teams to identify opportunities where AI can improve productivity, automation, data intelligence, and customer experiences.   This is a hands-on engineering role. Candidates should have a solid foundation in software development and APIs, with  some practical experience in C#/.NET . Deep expertise in .NET, React, or Angular is not required. We are more interested in candidates who understand modern AI/LLM technologies and can apply them effectively within enterprise software environments.   Key Responsibilities:    Design, develop, and integrate AI/LLM-powered capabilities into enterprise applications.   Evaluate and integrate LLM platforms, models, APIs, and AI services such as Azure OpenAI, OpenAI, or similar technologies.   Develop solutions using techniques such as:   Prompt engineering   Retrieval-Augmented Generation (RAG)   Embeddings and semantic search   Vector databases   Function/tool calling   Structured outputs   AI agents and agentic workflows   Context management   Build and consume RESTful APIs to integrate AI capabilities with existing enterprise applications.   Develop proof-of-concepts and production-ready AI solutions while evaluating model quality, accuracy, performance, cost, and scalability.   Leverage GitHub Copilot and other AI coding assistants to improve software development productivity while maintaining code quality and security.   Develop appropriate approaches for AI evaluation, testing, monitoring, and validation, including identifying hallucinations and unreliable model responses.   Work with business stakeholders to identify practical use cases for AI and translate business requirements into technical solutions.   Integrate AI solutions with enterprise data sources, databases, APIs, and existing applications.   Participate in architecture and technical design discussions related to AI-enabled applications.   Ensure AI solutions follow enterprise security, privacy, compliance, and DevSecOps practices.   Research emerging AI/LLM technologies and recommend approaches that can provide business value.   Troubleshoot complex technical issues involving applications, APIs, AI services, data, and infrastructure.   Mentor team members and share knowledge related to AI/LLM technologies and best practices.   Required Skills and Experience   AI / LLM — Primary Focus   2+ years of software engineering experience with hands-on exposure to Generative AI and/or LLM technologies.   Practical experience integrating LLMs or AI services into applications.   Understanding of LLM concepts such as:   Prompt engineering   Tokens and context windows   Embeddings   Vector search   RAG   Fine-tuning concepts   Function/tool calling   AI agents   Model evaluation   Experience working with one or more LLM/AI platforms such as Azure OpenAI, OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, or similar.   Experience developing AI-powered applications or prototypes using APIs, SDKs, or AI frameworks.   Experience using GitHub Copilot, ChatGPT, Claude, or other AI-assisted development tools.   Ability to understand, review, debug, and improve AI-generated code rather than simply relying on AI-generated output.   Understanding responsible AI, including security, privacy, hallucination risks, data protection, and appropriate handling of sensitive information.   Software Engineering   4+ years of professional software development experience.   Some hands-on experience with C#/.NET or .NET Core/.NET 6+. Deep .NET expertise is not required.   Strong understanding of software engineering fundamentals, including:   Object-Oriented Programming   SOLID principles   Design patterns   Algorithms and data structures   Clean and maintainable code   Experience developing and consuming RESTful APIs.   Experience working with relational databases such as SQL Server, PostgreSQL, or similar.   Experience with Git and modern source-control workflows.   Understanding of CI/CD and modern software development practices.   Strong debugging, troubleshooting, and problem-solving skills.   Experience working in Agile/Scrum environments.   Cloud / DevOps / Security   Experience working with cloud-based applications, preferably Azure, AWS, or Google Cloud.   Understanding cloud-native application architecture and microservices.   Familiarity with Docker and/or Kubernetes is a plus.   Experience with CI/CD tools such as Azure DevOps, GitHub Actions, Jenkins, or Harness.   Understanding of secure software development and DevSecOps practi