AI Scientist (focus on Agentic LLM)

about companyI am currently working with a company focusing on AI, LLM and Computer Vision.Hybrid working arrangement- 2 days office, 3 days WFH. Office location at near Buona Vista. 4 rounds of interview to offer stage.about jobDesign and implement robust frameworks to evaluate the performance of generative AI systems, including text and multi-modal models for Large Language Models (LLMs), including but not limited to GPT-based models, BERT, T5, and other state-of-the-art architecturesPerform technical AI evaluations on LLM including assessing them for robustness in performance, embedded biases, vulnerability to jailbreaks and prompt injection attacksWork with stakeholders to design strong LLM models, custom evaluation approaches and a suite of technical and analytical AI evaluation frameworks and toolsDefine and refine metrics for evaluating model performance, such as perplexity, BLEU, ROUGE, accuracy, coherence, factual consistency, and bias detectionLead efforts in curating and managing large, high-quality datasets for evaluating LLMsskills and requirementsMin 2 years for junior, 5 years for seniorExperience with Agentic AI or Agentic LLMStrong experience in evaluating LLMs using metrics such as perplexity, BLEU, ROUGE, and human-centered evaluation techniquesProven track record of managing and analyzing large, complex language datasets, including text preprocessing and tokenizationSolid programming skills in Python and experience building automated pipelines for continuous model evaluationTo apply online please use the 'apply' function, alternatively you may contact Stella at 96554170 (EA: 94C3609 /R1875382)Desired Skills and ExperienceLLM, Large language model, Agentic AI, Agentic LLM