Senior GenAI Application Engineer

Summary

Join Degreed as a Senior GenAI Application Engineer and design, build, and scale production-grade generative AI applications for our enterprise learning platform. You will own core GenAI application architecture, quality, and delivery, leveraging your technical expertise and understanding of business needs. Collaborate across teams, set technical standards, and shape Degreed's AI roadmap. This role requires a strong background in backend/API design, microservices, and experience with LLMs. You will build rapid prototypes, integrate LLM APIs, and transition successful prototypes into production systems. The ideal candidate will have 7+ years of Python software engineering experience and 2+ years of hands-on GenAI/LLM app development experience. Degreed offers a comprehensive benefits package to support your well-being, growth, and success.

Requirements

• 7+ years Python software engineering experience
• 2+ years hands-on GenAI / LLM app development (not model research)
• Up to date with the latest advancements in AI, LLMs, and GenAI best practices
• Strong background in backend/API design, microservices, CI/CD
• Proven experience building and scaling robust, production backend applications
• Practical experience integrating LLM APIs (OpenAI, Anthropic, Gemini, etc.)
• Experience with prompt engineering, RAG, agentic workflows, evaluation frameworks
• Cloud Exposure: Azure, GCP, or AWS
• Demonstrated ability to design for performance, resilience, testability, and scalability
• Experience with rapid prototyping and iterative product delivery
• Strong communication, code/design review, and collaboration skills

Responsibilities

• Architect, develop, and deploy scalable backend GenAI-powered applications for B2B use cases, ensuring performance, resilience, and maintainability
• Integrate, orchestrate, and optimize large language models and retrieval systems into enterprise products, driving business value
• Proactively set and uphold high standards for code quality, scalability, and best practices (through design/code reviews, mentoring, and technical leadership)
• Lead the design and implementation of prompt engineering, RAG pipelines, agentic workflows, and robust evaluation/testing strategies for GenAI features
• Build rapid prototypes, iterate on new AI product features, and transition successful prototypes into production systems
• Monitor, optimize, and troubleshoot GenAI services in a live cloud environment, proactively addressing risks and cross-module issues
• Collaborate closely with product, data, and engineering teams, translating open-ended requirements into actionable, scalable solutions
• Identify opportunities for technical improvement, advocate for and implement enhancements, and contribute to ongoing team learning and AI best practices
• Serve as a go-to expert in GenAI engineering, providing technical guidance and feedback across the team and supporting the technical roadmap

Preferred Qualifications

Applied ML/NLP background