Hire Yogesh M. - LLM Engineer

Engineered an autonomous CI/CD failure resolution agent using LLM-based root-cause analysis and agentic decision loops, reducing manual debugging effort by 60% and saving 8–12 engineering hours per week enabling a leaner on-call team structure. Designed and deployed end-to-end RAG pipelines integrating vector retrieval with fine-tuned LLMs, enabling domain-specific Q&A over internal technical documentation with significantly improved answer relevance and grounding. Built and maintained production-grade LLM automation systems using Python, LangChain, and HuggingFace Transformers covering the full ML lifecycle from data ingestion and prompt engineering through model evaluation, deployment, and monitoring.

* Contributed to AI compiler research and optimization efforts, gaining foundational experience in low-level model execution pipelines and the hardware-software interface for deep learning workloads. * Supported model performance benchmarking and analysis across compiler configurations, building proficiency in PyTorch and deep learning frameworks that underpins current LLM engineering work.

Delivered end-to-end data science projects under structured timelines, applying supervised learning techniques and data visualization to produce actionable insights building the analytical foundation for later ML engineering work