CharanTeja Kurakula

About

AI engineer who built an agentic, production-deployed LLM workflow for tobacco violation parsing and automated multi-case creation, using six specialized agents and a human-in-the-loop confidence-threshold routing design. Addressed data privacy constraints by generating synthetic datasets with LLM prompting, and orchestrated reproducible end-to-end pipelines in LangChain with robust testing and evaluation (precision/recall, micro-F1).

Key Strengths

• Built and deployed a multi-agent LLM system (6 agents) for tobacco violation parsing and multi-case creation
• Designed modular agent workflows (parser/classifier/validator/case creator) with unit + integration testing
• Implemented human-in-the-loop routing using calibrated confidence thresholds for safer decisions
• Generated privacy-preserving synthetic datasets using LLM prompting with sample-guided generation
• Compared multiple model families (LogReg, SVM, Transformers) and selected best-performing approach
• Orchestrated end-to-end ML pipelines with LangChain including retries, error isolation, and reproducibility/versioning

Experience

Education

Skills

Languages

Certifications