Anjali Chandana

About

AI Engineer at DXC Technology who has shipped production LLM/NLP systems on AWS (SageMaker, FastAPI) and optimized them for real-time latency and unpredictable traffic using quantization, batching, and autoscaling. Strong MLOps and monitoring discipline (MLflow, CloudWatch, SageMaker Model Monitor) and proven business impact—delivered models with 92% predictive accuracy and cut enterprise decision-making time by 30% through close collaboration with product managers.

Experience

Education

Key Strengths

• Built and deployed production NLP pipeline for enterprise text classification and entity recognition using Hugging Face Transformers
• Reduced transformer inference latency via quantization and asynchronous batching on SageMaker
• Designed scalable ML services with SageMaker endpoint autoscaling and stateless FastAPI architecture
• Implemented end-to-end MLOps orchestration (SageMaker Pipelines, Lambda, Docker, CI/CD, MLflow) for automated training-to-deployment workflows
• Strong post-deployment monitoring approach: MLflow + SageMaker monitoring with CloudWatch for performance, drift, and system health
• Pragmatic model tradeoff decisions (BERT to DistilBERT + quantization) to meet real-time latency targets while maintaining accuracy
• Added lightweight semantic retrieval with sentence embeddings to improve precision on domain-specific edge cases
• Cross-functional delivery with product managers; deployed models achieving 92% predictive accuracy and reducing enterprise decision-making time by 30%
• Communicates AI impact to non-technical stakeholders using business metrics and dashboards