AI Engineer

Job Description – AI Engineer
Position Overview
The AI Engineer is responsible for designing, building, and optimizing AI and ML-powered product capabilities that elevate intelligence and automation across the InvoiceCloud platform. This role delivers high-impact features, contributes to modern AI architecture, and drives experimentation and performance improvements for production-grade AI solutions.
The AI Engineer collaborates closely with cross-functional stakeholders to translate requirements into robust and scalable implementations and plays a key role in improving developer productivity through reusable components, frameworks, and automation.
Success Profile
Results Driven
• Owns delivery of complex AI-driven product features and model enhancements.
• Improves accuracy, scalability, latency, and reliability of deployed models.
• Contributes to roadmap planning and advances experimentation and deployment capability.
Takes Ownership
• Builds reliable and secure AI pipelines, APIs, and monitoring capabilities.
• Partners with engineering and product teams to ensure consistent delivery.
• Troubleshoots and resolves model performance issues.
Innovative
• Experiments with GenAI tools and LLM frameworks including LangChain, Semantic Kernel, and Azure OpenAI.
• Identifies automation and efficiency improvements with MLOps workflows.
• Researches and applies emerging AI technologies to enhance platform capabilities.
Customer Centric
• Designs AI features that improve user experience and operational outcomes.
• Incorporates feedback loops to refine model accuracy and performance.
• Participates in responsible AI standards and reviews.
Requirements
• 5 or more years of software engineering experience with at least 2 to 3 years building AI or ML or LLM-based applications.
• Hands-on experience deploying AI models in production and integrating vector search or retrieval augmented systems, Fast API.
• Strong programming skills in Python and familiarity with C#.
• Expertise with Python and C# and experience with Semantic Kernel, LangChain, Azure OpenAI, Fast API, and vector databases.
• Strong understanding of model evaluation, prompt tuning, inference optimization, and observability.
• Excellent communication and leadership skills with experience mentoring engineers and influencing architecture.
• Experience with prompt engineering, model evaluation, and inference optimization.
• Strong analytical, communication, and team collaboration skills.