Basanth Yajman

Architected a fault-tolerant LangGraph multi-agent pipeline with GPT-4 tool-calling for geospatial data, analyzing structural inequity in Large Language Models (LLMs) for non-English scripts. Optimized downstream causality pipelines using PyTorch and R, directly improving risk analytics precision by 15%.

Fine-tuned NASA Prithvi Vision Transformer via MAE pretraining in PyTorch for high-risk satellite detection. Architected scalable, cloud-native REST APIs on AWS EC2 & Lambda with Kubernetes orchestration and Prometheus observability, cutting spatial inference latency by 25%.

Developed Kafka-backed event-driven microservices on Azure Databricks with exactly-once semantics. Deployed RESTful XGBoost inference APIs via blue-green deployments, slashing infrastructure costs by $400K and reducing unplanned operational failures by 20%.

Built low-latency RESTful APIs in Python/C++ for production messaging architectures. Engineered stateful stream processing via Kafka, refactored PostgreSQL materialized views tuning query latency (-28%), and deployed zero-downtime microservices using GitLab CI/CD and Docker.