Senior AI Systems Engineer: LLMs, RAG & Production

Insperity

Houston (TX)

On-site

USD 140,000 - 190,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Insperity is seeking an Artificial Intelligence Engineer III to design, deliver, and own complex, production‑grade AI systems addressing high‑impact business problems. You will apply software, data science, ML, and LLM engineering to build AI‑powered applications, model‑driven solutions, and automated workflows with reliability and enterprise alignment.

You will collaborate across product, platform teams, and stakeholders, mentor others, and contribute to engineering standards while ensuring

Qualifications

Bachelor’s degree in Computer Science, Software Engineering, Data Science, or a related technical field
Five or more years of professional experience spanning software engineering, data science, machine learning engineering, or AI system development
Advanced proficiency in Python, APIs, testing, and system design
Experience with large-scale data platforms such as Snowflake, Databricks, Redshift, or Synapse
Strong applied knowledge of machine learning and AI concepts, evaluation techniques, and failure modes
Hands-on experience building and deploying LLM-based systems using enterprise-grade platforms
Experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel
Understanding of data quality, feature relevance, and model behavior across structured and unstructured data
Experience deploying, monitoring, and iterating on AI systems in production
Ability to balance accuracy, cost, risk, and scalability
Strong communication and leadership skills to influence technical direction

Responsibilities

Design and own end-to-end AI solutions, including LLM-based applications and hybrid approaches
Build and operate complex AI systems such as agentic workflows and RAG platforms
Evaluate ambiguous business problems and select AI patterns and architectures
Define evaluation strategies, metrics, and feedback loops to measure model impact
Lead development of data pipelines, feature strategies, and evaluation datasets
Own production readiness including performance, reliability, cost, and observability
Identify and mitigate risks related to bias, data leakage, and unintended AI behavior
Collaborate cross-functionally with product, platform teams, and stakeholders
Mentor and provide technical guidance to team members
Contribute to AI engineering standards and best practices