The AI/ML Developer (Full Stack) is a hands-on engineer within the First American Technology organization, focused primarily on building, customizing, and integrating Large Language Model (LLM)–based solutions. This role is ideal for a full stack developer with 3–5 years of experience who has transitioned into AI/ML and is passionate about Generative AI, prompt engineering, and creating custom GPT-based solutions.
The individual will work closely with onshore leads, offshore teams, and business stakeholders to deliver AI-powered applications, while actively coding, experimenting, and supporting AI solutions in production.
- Design, build, and maintain LLM-powered solutions including custom GPTs and domain-specific assistants.
- Develop and optimize prompts, system instructions, and context strategies for accuracy and reliability.
- Implement prompt chaining, tool calling, and basic agentic workflows.
- Build and support Retrieval-Augmented Generation (RAG) pipelines using vector databases.
- Evaluate, test, and improve LLM outputs using defined quality and safety criteria.
- Apply responsible AI principles, safety guardrails, and governance standards in all implementations.
- Develop full stack AI-enabled applications including backend services, APIs, and UI integrations.
- Integrate LLM capabilities into existing enterprise applications.
- Build reusable services and components to support AI features.
- Debug and resolve application or AI-related issues impacting functionality or user experience.
- Develop and deploy AI solutions on Azure and/or AWS.
- Support CI/CD pipelines for application and AI workloads.
- Assist with MLOps workflows including model versioning, deployment, and monitoring.
- Ensure solutions are secure, reliable, and cost-aware in production environments.
- 3–5 years of overall software engineering experience.
- Strong full stack development background.
- Proficiency in Python and solid programming fundamentals.
- Hands-on experience with LLMs, Generative AI, and prompt engineering.
- Experience creating or customizing GPT-based solutions.
- Familiarity with RAG architectures and vector databases.
- Cloud experience with Azure and AWS.
- Basic understanding of MLOps, DevOps, and production support practices.
- Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.
- Frontend experience with modern frameworks is a plus.