{"schemaVersion":"jobsearcher.job.v1","id":"943de4aaa3577b90e700dece","url":"https://jobsearcher.com/jobs/943de4aaa3577b90e700dece","canonicalUrl":"https://jobsearcher.com/jobs/943de4aaa3577b90e700dece","title":"Python GenAI Model Evaluator","description":"Model EvaluatorPlease share 2 onsite profiles for Model Evaluators. Location can be either SCV or Austin. Billing: $78/HrTechnical SkillsStrong understanding of LLMs, generative AI, and transformer-based architectures.Experience with Python, data analysis, and model evaluation frameworks.Familiarity with prompt engineering, embeddings, RLHF/RLAIF, and LLM-based scoring methods.Experience building evaluation datasets and working with annotation platforms.Understanding of safety alignment, bias detection, and adversarial testing.Tools & PlatformsML/AI frameworks: PyTorch, TensorFlow, HuggingFace, LangChain.Evaluation/annotation tools: Scale AI, GroundTruth, Labelbox, Prodigy.Prompt testing tools: Weights & Biases, MLflow, OpenAI evals, LLM-as-a-judge pipelines.","company":"Clifyx","rawCompany":"clifyx","city":"Austin","state":"TX","isRemote":false,"isActive":false,"createdAt":"2026-09-11T12:40:05.855Z","occupations":[{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1251.00","title":"Computer Programmers","slug":"computer-programmers"}],"industries":[{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"},{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Python GenAI Model Evaluator","description":"Model EvaluatorPlease share 2 onsite profiles for Model Evaluators. Location can be either SCV or Austin. Billing: $78/HrTechnical SkillsStrong understanding of LLMs, generative AI, and transformer-based architectures.Experience with Python, data analysis, and model evaluation frameworks.Familiarity with prompt engineering, embeddings, RLHF/RLAIF, and LLM-based scoring methods.Experience building evaluation datasets and working with annotation platforms.Understanding of safety alignment, bias detection, and adversarial testing.Tools & PlatformsML/AI frameworks: PyTorch, TensorFlow, HuggingFace, LangChain.Evaluation/annotation tools: Scale AI, GroundTruth, Labelbox, Prodigy.Prompt testing tools: Weights & Biases, MLflow, OpenAI evals, LLM-as-a-judge pipelines.","datePosted":"2026-09-11T12:40:05.855Z","dateModified":"2026-09-11T12:40:05.855Z","hiringOrganization":{"@type":"Organization","name":"Clifyx","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Austin","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"943de4aaa3577b90e700dece"},"url":"https://jobsearcher.com/jobs/943de4aaa3577b90e700dece"}}