AI Engineer (Plano)

Location: Plano, TX, US; onsite 3 days per week

Company

Work with a multinational telecommunications technology leader on enterprise-scale AI infrastructure used by millions of users.

What you will do

• Build and maintain an LLM evaluation framework with golden datasets, regression tests, scoring rubrics, quality thresholds, and trend tracking for non-deterministic outputs.
• Implement observability for LLM pipelines, including structured logging, metrics, dashboards, alerting, latency analysis, error taxonomies, and token and cost tracking.
• Design and integrate tool-calling and agent skills into data pipelines and services, including function calling, tool interfaces, input/output schemas, guardrails, and structured outputs.

Requirements

• 5+ years of hands-on experience in Software & Data Engineering and GenAI, including agentic design, development, and production deployment.
• Hands-on experience with LangGraph, LangChain, and agentic systems in production.
• Experience productionizing AI/ML or LLM-powered workflows using LangGraph, LangChain, CrewAI, or similar frameworks, with a focus on reliability, reproducibility, and auditability.
• Strong understanding of LLMOps fundamentals, including prompt, model, and configuration versioning and traceable run metadata.
• Hands-on experience with Python, PySpark/Spark, NoSQL databases including MongoDB, SQL and PostgreSQL, Redis, Databricks, Delta Lake, and Azure Cloud.
• Demonstrated curiosity and self-learning ability in the fast-evolving GenAI industry, with the ability to iterate quickly and harden solutions for production.
• Experience with API reliability patterns for model calls, including rate limiting, retries and backoff, circuit breakers, timeouts, idempotency, replay, and backfill.

Culture & Benefits

• Hands-on ownership of AI evaluation and observability systems.
• Exposure to large-scale, real-world AI infrastructure challenges.
• Collaboration with experienced engineers on novel technical problems.
• Opportunity to shape practices for responsible, high-performing AI at global scale.