LLM Reliability Engineer: Production AI/ML & Observability

Elite Technical; Plano (TX); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Elite Technical is seeking an AI Engineer to join our Plano team to build and maintain an LLM evaluation framework, focusing on non-deterministic outputs and observability. You will design tool-calling capabilities and integrate agent skills into data pipelines while ensuring reliability and auditability.

Ideal candidates have hands-on Python, PySpark, databases (MongoDB, PostgreSQL, Redis), Databricks/Delta Lake, and Azure Cloud experience, with a passion for GenAI and scalable production

Qualifications

• Productionizing AI/ML or LLM powered workflows with reliability and auditability.
• LLMOps fundamentals including versioning and traceable run metadata.
• Proficiency in Python, PySpark, NoSQL/SQL databases, and cloud services.
• Self-driven learning in GenAI with rapid iteration to production.
• Experience with model call reliability patterns (rate limiting, retries, circuit breakers, timeouts).

Responsibilities

• Build and maintain an LLM evaluation framework with datasets and scoring thresholds.
• Add observability for LLM pipelines including logs, metrics, dashboards, and cost tracking.
• Design and integrate tool-calling/agent skills into data pipelines or services.

Skills

AI/ML productionizing

LLMOps

Python

PySpark

MongoDB

PostgreSQL

Redis

Databricks

Delta Lake

Azure Cloud

GenAI curiosity

Tools

LangGraph

LangChain

CrewAI

Job description

Elite Technical is seeking an AI Engineer to join our Plano team to build and maintain an LLM evaluation framework, focusing on non-deterministic outputs and observability. You will design tool-calling capabilities and integrate agent skills into data pipelines while ensuring reliability and auditability.

Ideal candidates have hands-on Python, PySpark, databases (MongoDB, PostgreSQL, Redis), Databricks/Delta Lake, and Azure Cloud experience, with a passion for GenAI and scalable production