Design and implement high-performance RESTful or GraphQL APIs to expose AI model functionality to front-end applications and external services.
Integrate Large Language Models (LLMs) and custom machine learning models into backend architectures, often using frameworks like LangChain, LangGraph, or FastAPI.
Build and maintain data ingestion pipelines and vector databases (e.g., Pinecone, Weaviate) to support Retrieval-Augmented Generation for AI agents.
Deploy and orchestrate containerized services using Docker and Kubernetes on cloud platforms like AWS, GCP, or Azure.
Implement real-time monitoring and alerting for AI system health, including tracking model performance, latency, and drift.
Design testing strategies for non-deterministic AI outputs, including the implementation of guardrails and safety constraints.
Own the full development lifecycle for services in a production SaaS environment. This includes establishing automated code coverage goals, rigorous code reviews, defining SLOs, and ensuring a fast and effective incident response process
Works as part of a team.
Mentor colleagues in AI software engineering best practices
Performs code reviews of junior software engineers and provides constructive feedback on any findings, both verbal and in writing.
Read and follow the Underwriters Laboratories Code of Conduct, and follow all physical and digital security practices
Performs other duties as directed.
Qualifications
University degree in Computer Science or a related discipline.
5–8 years of professional experience in software engineering or backend systems.
2–3 years relevant experience in AI technologies — building APIs, integrating LLMs, designing RAG pipelines, and deploying scalable microservices.
Strong applied expertise with frameworks like LangChain, FastAPI, Kubernetes, and cloud platforms.
Advanced technical knowledge and/or software development experience.
Advanced working knowledge in software application or specific program language requirements of software work.
