Shashank Bijarapu

About

AI/ML engineer (Merkle) with hands-on experience deploying RAG-based LLM applications and real-time recommendation engines into production. Strong in cloud/on-prem architectures, GPU autoscaling, caching, and network optimization—delivered measurable latency reductions (40–70%) and improved retrieval relevance by systematically benchmarking chunking/embedding configurations and validating pipelines via CI/CD.

Experience

Education

Key Strengths

• Production deployment of RAG-based LLM apps with retrieval quality and latency improvements
• Data-driven retrieval optimization (chunk size/overlap/embedding experiments using precision/recall and cosine similarity)
• Caching strategy implementation (in-memory + semantic) reducing vector DB load and cutting latency ~40%
• Cross-layer debugging across software, GPU hardware metrics, and network traces to isolate root causes
• Real-time inference optimization (batching, removing redundant computation) plus GPU autoscaling and traffic rerouting cutting latency ~70% and eliminating failed predictions
• Customer-specific Python customization with modular, config-driven design and unit tests for maintainability
• On-site client collaboration translating workflow observations into system changes that improved adoption