Machine Learning Engineer LLMs & Information Extraction

Job Title: Machine Learning Engineer LLMs & Information Extraction

Location: Dallas, TX

Job Summary:

We are seeking a highly skilled Machine Learning Engineer with hands-on experience in building and deploying production-grade AI/ML systems particularly those focused on large language models (LLMs) and information extraction workflows, not chatbot development.

This role will involve designing, fine-tuning, and integrating open-source and commercial LLMs (e.g., OpenAI, Cohere, Hugging Face) into systems that perform tasks such as prompt engineering, document analysis, knowledge retrieval, and workflow automation. The ideal candidate will bring a strong foundation in Python, deep learning frameworks, and real-world experience building scalable ML systems in production.

Key Responsibilities:

• Design and deploy end-to-end LLM-powered systems for tasks like data extraction, information retrieval, summarization, and document classification
• Engineer prompts and evaluation frameworks to optimize performance of commercial (OpenAI, Anthropic, Cohere) and open-source LLMs (e.g., Mistral, LLaMA, Falcon)
• Develop robust, production-grade ML pipelines that include model fine-tuning, inference optimization, and post-processing logic
• Work with cross-functional teams to integrate ML components into broader data or business process automation workflows
• Monitor and improve system performance, latency, accuracy, and cost-efficiency
• Stay current with advances in foundation models, open-source ML tools, and deployment techniques

Must-Have Qualifications:

• 3+ years of experience building and deploying machine learning systems in production
• Expert-level proficiency in Python and modern ML libraries such as PyTorch, TensorFlow, and Hugging Face Transformers
• Hands-on experience working with LLMs (e.g., OpenAI, Anthropic, Cohere, or open-source models)
• Strong understanding of prompt engineering, fine-tuning, embeddings, and LLM evaluation
• Experience with data extraction, semantic search, NER, or document processing
• Familiarity with inference deployment on cloud or on-prem infrastructure (e.g., AWS Sagemaker, Docker, REST APIs)

Nice-to-Haves:

• Experience with vector databases (e.g., FAISS, Pinecone, Weaviate)
• Familiarity with LangChain, LLM orchestration, or RAG (retrieval-augmented generation) systems
• Exposure to workflow automation, document pipelines, or enterprise data systems

• Understanding of evaluation metrics for LLM-driven applications