Senior LLM/Reasoning Engineer

Senior LLM/Reasoning Engineer – Join Our Team .job-posting-container {font-family: Arial, sans-serif; line-height: 1.6; color: #333; margin: 0; padding: 20px; background-color: #ffffff; box-sizing: border-box;} .job-posting-container * {box-sizing: border-box;} .job-posting-content {background-color: #ffffff; padding: 30px; max-width: 800px; margin: 0 auto; box-shadow: 0 0 10px rgba(0,0,0,0.1); border-radius: 10px;} .job-posting-container h1, .job-posting-container h2 {color: #004080; margin: 15px 0;} .job-posting-container h1 {font-size: 22px;} .job-posting-container h2 {font-size: 20px; border-bottom: 1px solid #ccc; padding-bottom: 5px; margin-top: 30px;} .job-posting-container ul {margin-left: 20px;} .job-posting-container .section {margin-bottom: 25px;} .job-posting-container .highlight {background-color: #eef6ff; padding: 15px; border-left: 4px solid #004080; margin-bottom: 15px; border-radius: 5px;} .job-posting-container strong {color: #333;} .job-posting-container li {margin-bottom: 8px;} Senior LLM/Reasoning Engineer Location: Austin, Texas, USA | Type: Contract (CTC, W2) | Experience: 8+ years Position Overview This role focuses on building and optimizing the reasoning layer that transforms deterministic detections into reliable, measurable outcomes. Success is defined by accuracy against established decisions and an increasing share of items processed without human intervention. Why Join Us? Work on cutting-edge LLM applications with measurable production impact Collaborate with domain experts to build robust AI systems Drive innovation in model evaluation and continuous improvement Opportunity to shape the future of automated reasoning systems Key Responsibilities Design the reasoning tier including structured-output disposition schemas, context-engineered prompts, and curated exemplar sets Build and maintain gold standard datasets while measuring precision, recall, and confidence calibration Implement abstention mechanisms and self-consistency sampling for high-stakes decisions Mine reasoning traces to extract deterministic rules and optimize model routing strategies Develop regression suites to ensure AI layer changes do not degrade quality Partner with domain experts to convert verdicts into exemplars and noise filters Qualifications 8+ years of experience with demonstrated impact taking LLM applications into production Strong Python skills with production-grade development experience Deep expertise in LLM application engineering including structured generation, context engineering, and evaluation Proven track record in evaluation engineering with golden sets, calibration, and regression benchmarking Experience with AWS Bedrock, Claude, or equivalent frontier models in production environments Sound understanding of statistics and ML fundamentals with ability to design around correlated failure modes Working knowledge of RAG systems, retrieval quality metrics, and grounding techniques Ready to Apply? Take the next step in your career with this exciting opportunity to work on advanced LLM systems. Contact: naved.mohd@dprsolutionsinc.com Phone: 5714636046 Take the next step in your career!