AI Engineer (LLM)

TL;DR

AI Engineer (LLM): Design, develop, and optimize LLM-powered applications using prompt engineering, fine-tuning, and retrieval-augmented generation (RAG) architectures. Focus on building agentic workflows, multi-step AI pipelines, and integrating LLMs into production systems solving complex performance and scalability challenges.

Location: Dallas-Fort Worth Metroplex, TX. 2-3 days on-site. Must be authorized to work legally in the US without sponsorship, now or in the future.

Compensation: $50 - $70/hr

Company

Execution company focused on technology integration, AI, data management, analytics, UX, and digital experiences for client digital transformation.

What you will do

• Design, develop, and optimize LLM-powered applications using prompt engineering, fine-tuning, and RAG architectures.
• Build and maintain agentic workflows and multi-step AI pipelines with frameworks like LangChain, LlamaIndex, or AutoGen.
• Evaluate, select, and integrate LLMs from providers like OpenAI, Anthropic, Mistral, Llama, or Gemini.
• Collaborate with data, product, and engineering teams to deploy AI solutions from prototype to production.
• Monitor model performance, identify failure modes, implement improvements, and document architecture decisions.
• Maintain clean, scalable Python codebases.

Requirements

• 4–7 years of software engineering experience, with at least 2 years focused on AI/ML or LLM development.
• Strong Python proficiency.
• Hands-on experience with prompt engineering techniques (chain-of-thought, few-shot, system prompting).
• Experience fine-tuning LLMs (LoRA, PEFT, instruction tuning).
• Solid understanding of RAG architecture (chunking, embedding models, retrieval optimization).
• Experience designing agent workflows (tool use, memory, planning loops).
• Familiarity with multiple LLM providers and model trade-offs.

Nice to have

• Experience with vector databases (Pinecone, Weaviate, Chroma, pgvector).
• Cloud platform experience (AWS, Azure, GCP).
• MLOps exposure (MLflow, Weights & Biases).
• Retail industry background (personalization, recommendations, forecasting).
• LLM evaluation frameworks (Ragas, DeepEval).
• Multimodal models or vision-language applications.

Culture & Benefits

• Health, Dental, Vision Insurance, HSA contributions, FSA, LSA (for W-2 Employment).
• Disability, Life and AD&D Insurance (employer-paid).
• Employee Assistance Program (EAP).
• 401(k) with 1% employer match.
• Career growth opportunities and skill development.
• Team engagement activities and company events.