Lead AI / LLM Engineer

Programmers.io; Dallas (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

Programmers.io in Dallas, Texas seeks a seasoned GenAI/LLM engineer to design, implement and optimize AI-powered applications. You will architect RAG-enabled systems, craft prompts, and fine-tune models for robust, production-grade deployments.

Key work includes integrating LangChain and LlamaIndex with vector databases, ensuring safety, guardrails and high-quality responses across AWS or GCP environments. This role focuses on scalable, reliable AI solutions in a fast-paced setting.

Qualifications

• Strong hands-on experience building GenAI and LLM-based applications.
• Experience with Retrieval Augmented Generation (RAG) architectures.
• Expertise in prompt engineering, fine-tuning, evaluation and optimization of models.
• Strong Python development skills for production-grade applications.
• Experience with LangChain, LlamaIndex and vector databases.
• Knowledge of conversational guardrails, AI safety, response validation and hallucination prevention.
• Experience deploying scalable AI solutions in AWS or GCP environments.

Skills

GenAI & LLM development

RAG architecture

Prompt engineering

LLM fine-tuning

Model evaluation & optimization

Python production-grade development

LangChain

LlamaIndex

Vector databases

AI safety & guardrails

AWS/GCP deployment

Job description

Key Requirements:

• Strong hands-on experience building GenAI and LLM-based applications.
• Experience with RAG (Retrieval Augmented Generation) architecture and AI assistants.
• Expertise in Prompt Engineering, LLM fine-tuning, evaluation, and model optimization.
• Strong Python development skills with production-level application experience.
• Experience with LangChain, LlamaIndex, and Vector Databases.
• Knowledge of conversational guardrails, AI safety, response validation, and hallucination prevention.
• Experience deploying scalable AI solutions in AWS or GCP environments.