Job Summary:
As an Artificial Intelligence (AI) Engineer at Medefy Health, you will work with the Data Science team to design, develop, and deploy intelligent systems using cutting-edge machine learning technologies. This role combines strong software engineering fundamentals with expertise in AI/ML model development, with a focus on building and deploying AI agents and LLM-powered applications. You'll work on production-scale systems that directly impact on our customers and business outcomes.
About our awesome company, Medefy Health...
Medefy Health (www.Medefy.com) is a leading SaaS benefits navigation company, dedicated to simplifying the way employees’ access and utilize their benefits. Our mission is to drive better health and financial outcomes for our users while supporting HR teams and broker partners with seamless, data-driven solutions.Â
Our company is headquartered in Tulsa, OK. We’re proud to be Oklahoma’s #1 fastest-growing company and rated by Inc. Magazine as the 37th fastest-growing tech company and the 288th fastest-growing company overall in the USA, and our story is still being written!
Healthcare is only getting more complicated, and more expensive, for employers and their employees. This is where Medefy Health comes in. We’re on a mission to eliminate the stress on hard-working families caused by an impossible to navigate healthcare system. All while saving them, and their employers, a significant amount of time and money. We demolish barriers between healthcare and the people who need it, and we need your help to further our mission!
Job Duties & Responsibilities:
- Core Engineering:
- Design and implement machine learning models and AI systems from conception to production deployment
- Build and optimize AI agents that can operate autonomously, perform reasoning, and make intelligent decisions
- Develop and maintain scalable ML pipelines, data processing workflows, and model serving infrastructure
- Integrate AI capabilities into existing applications and services through APIs and microservices
- LLM and AI Agent Development:
- Deploy Large Language Models for specific business applications
- Design and implement AI agents using frameworks (like LangChain) or other/custom architecture
- Implement prompt engineering, retrieval-augmented generation (RAG), and agentic workflows
- Optimize agent behavior through feedback loops, reinforcement learning, user interaction, and fine-tuning
- Production Systems:
- Deploy ML models to production environments using containerization (Docker, Kubernetes) and cloud platforms (Azure)
- Monitor model performance, implement A/B testing, and maintain model lifecycle management
- Collaborate with DevOps teams to ensure robust, scalable, and reliable AI system deployments
- Implement safety mechanisms, guardrails, and ethical AI practices
- Collaboration and Leadership:
- Work closely with data scientists, product managers, and engineering teams to translate business requirements into technical solutions
- Document technical decisions, model architecture, and system designs and communicate to non-technical audiences
- Stay current with latest AI/ML research and apply cutting-edge techniques to solve business problems
- Performs other duties as assigned