Engineering focus centered on LLM systems, agentic architectures, retrieval pipelines, and large-scale backend services built for high availability, low latency, and production reliability. Work spans the design and implementation of autonomous agents, RAG frameworks, microservice-based AI platforms, and data-centric workflows capable of operating at enterprise scale. Technical expertise include: • LLM Systems Engineering: tool-calling reliability, function-execution pipelines, multi-agent coordination, contextualization strategies, evaluation frameworks • RAG & Retrieval Systems: vector databases, hybrid search, embedding optimization, caching layers, document routing, structured retrieval • Distributed & Backend Systems: async Python, FastAPI/Node.js microservices, API gateways, service mesh patterns, observability tooling, high-throughput data flows • ML Infrastructure: ONNX/Triton inference optimization, GPU/CPU serving strategies, batch/stream processing, Ray-based distributed workloads, CI/CD for ML and LLM models • Data & Knowledge Systems: knowledge-graph construction, semantic query pipelines, ETL and data quality automation, schema-driven modeling • Cloud & DevOps: Kubernetes, Docker, AWS, GCP, autoscaling strategies, monitoring/alerting stacks, IaC workflows Engineering philosophy centers on scalable systems design, correctness guarantees, performance optimization, and automation-first workflows. Strong emphasis on aligning LLM and agentic systems with production constraints such as latency budgets, fault tolerance, data governance, and cross-service integration.