The
AI Engineer I is responsible for building, testing, and maintaining components of AI-powered software applications under the guidance of senior engineers. As part of the AI & Analytics Innovation Team, this role will work together with engineers and data scientists to implement well-defined features of LLM-based applications that drive operational outcomes for internal teams as well as customers. The AI Engineer I will develop application code, integrate AI model APIs, support data preparation, and build the engineering fundamentals required for production-quality AI systems.
RESPONSIBILITIES, other duties may be assigned.- Implement well-defined features of AI-powered applications based on designs and specifications from senior engineers
- Integrate LLM APIs into applications, including prompt templates, structured outputs, and basic tool / function calling
- Build and maintain components of retrieval-augmented generation (RAG) pipelines: data ingestion, parsing, chunking, embedding generation, and basic retrieval
- Assist with data preparation and pipelines (cleaning, transformation, ingestion) to support AI / Analytics systems
- Write unit tests and run evaluation scripts to measure output quality, latency, and accuracy of AI features
- Support deployment and monitoring of services: containerization, logging, metrics, and alert investigation on owned components
- Work collaboratively as part of a distributed, fast paced team
- Participate fully in code review, version control, sprint ceremonies, and documentation
Assist with maintaining deployed API based systems and infrastructure
BASIC QUALIFICATIONS- 0-2 years of hands-on experience in software development (internships and substantial academic or personal AI projects count) OR BS degree in computer science or equivalent
- Demonstrated record of work ethic, team collaboration, accountability, and holding yourself and your team to higher standards
- Experience with Python application development
- Software engineering foundations: comfortable with Git / version control, writing clean and readable code, basic data structures and algorithms, debugging, and working in the terminal / command line
- Understanding of how the web works at a basic level: HTTP / REST APIs and JSON
- Hands-on exposure to LLM APIs and prompt engineering through projects, coursework, or professional work
- Basic understanding of how LLMs work in practice: tokens, context windows, and how they affect cost and behavior
- Working knowledge of SQL
- Strong verbal / written communication skills
PREFERRED QUALIFICATIONS- Familiarity with embeddings and vector search, and at least one vector database (e.g., pgvector, Pinecone, Chroma, Qdrant)
- Familiarity with an LLM orchestration framework (e.g., LangChain, LlamaIndex, LangGraph)
- Exposure to cloud-based application development (AWS / Azure) and containerization (Docker)
- Familiarity with an AI evaluation framework or LLM-as-a-judge concepts
- Awareness of open-source / locally run models and tooling (e.g., Hugging Face, Ollama)
- A portfolio of shipped AI projects or open-source contributions
