Location: Dallas, TX
Core
Building production LLM systems including RAG assistants over large document sets, LLM evaluation harnesses, and fine-tuned models.
Role type
Applied AI / ML engineer (LLM systems)
Builds
Production LLM systems, RAG assistants, evaluation harnesses, fine-tuned models
Domain
Financial services, Large Language Models, MLOps
Deliverable
production ML models
Required skills
Python, LangGraph, LangChain, RAG, supervised fine-tuning, PyTorch, Spark, Docker, Kubernetes, cloud platforms (AWS/Azure/GCP)
Preferred skills
MCP, Anthropic/OpenAI APIs, MLflow, LLaMA/Mistral model fine-tuning
Responsibilities
Building RAG assistants over large document sets, developing LLM evaluation harnesses for hallucination and prompt-injection, fine-tuning open-source models
Seniority
Mid-level, hands-on IC
Sourced via hn_whoishiring · Listed on CareerPlan, which tracks 854,000+ jobs from 20+ sources.