Senior AI Software Engineer

Empyrean•Houston, TX

1d•Remote

About The Position

As a member of the Enterprise Product Development Team, the Senior AI Software Engineer designs and builds intelligent, AI‑powered conversational platforms and automation solutions. This role focuses on applying large language models (LLMs) to real‑world use cases such as chat experiences, document understanding, and workflow automation. The Senior AI Software Engineer collaborates closely with product, engineering, and platform teams to deliver secure, scalable, and reliable AI solutions that improve how employees and clients interact with benefits and enterprise systems.

Requirements

Strong software engineering experience with Python and/or JavaScript
Hands‑on experience building AI or machine‑learning powered applications
Experience working with LLMs, embeddings, and vector databases
Familiarity with RAG architecture and modern AI tooling
Experience deploying and operating services in the cloud (AWS preferred)
Understanding of secure system design and enterprise integrations
Strong communication skills and ability to work cross‑functionally
Ability to work in an agile, fast-paced environment
6+ years of professional software engineering experience
Experience building and supporting production systems

Nice To Haves

Bachelor’s degree in Computer Science, Engineering, or a related field preferred, but not required
Equivalent professional experience accepted in place of a degree
Experience in healthcare, benefits, or other regulated industries is a plus

Responsibilities

Design and build AI‑powered conversational and automation platforms used in production
Develop and maintain Retrieval‑Augmented Generation (RAG) pipelines for complex content such as benefit documents and policies
Build intelligent agents that automate multi‑step business workflows
Integrate large language models (LLMs) into enterprise and legacy systems in a secure and compliant way
Implement guardrails, monitoring, and human‑in‑the-loop checkpoints to ensure AI outputs are reliable and auditable
Improve AI response quality through prompt engineering, testing, and optimization
Design data ingestion pipelines to process unstructured content like PDFs and benefit summaries
Apply modern retrieval techniques (vector search, keyword search, re‑ranking) to improve answer accuracy
Deploy AI solutions using cloud‑native architectures (serverless and container-based)
Monitor and optimize system performance, latency, and cost
Participate in design discussions and contribute to technical decision‑making
Mentor team members and share best practices
Perform other job‑related duties as assigned