Found Description
Can reach us on Candidate official notice exceeding 30 days are not eligible should be available for F2F interview on week working day Exp-4-9 Years AIML Evaluation Handson LLM evaluation experience GPT Claude Llama Evaluation metrics BLEU ROUGE perplexity F1 exact match Hallucination rate grounding rate factual accuracy measurement Toxicity and safety evaluation frameworks Technical Strong Python programming ML frameworks HuggingFace LangChain LlamaIndex Prompt engineering and testing methodologies API testing for AI endpoints AI Agent Testing Multistep AI agent workflow understanding Tool chaining function calling agent orchestration testing Context injection memory recovery path validation