Uday kumar swamy

About

Built a production LLM-agent framework for a startup that performs daily financial/trading analysis by combining live market data with internal tools, including a centralized memory module to prevent context drift and reduce hallucinations. Also implemented an Airflow-orchestrated retail price forecasting pipeline deployed to AWS endpoints, scaling parallel workloads via Kubernetes Executor and validating systems with rigorous functional + LLM-specific metrics and cross-team collaboration.

Experience

Education

Key Strengths

• Built and deployed an LLM-powered financial analysis/trading strategy agent with risk/reward explanations
• Designed centralized agent memory to persist intermediate results and reduce context drift/hallucinations
• Optimized LLM cost/latency via caching, adaptive throttling, and compressed context using cheaper summarization models
• Established LLM-specific evaluation metrics (tokens/request, TPM/RPM, cache hit rate, latency) plus functional/integration testing
• Production workflow orchestration with Airflow for end-to-end ML pipelines (data → features → training → tuning → packaging → deployment)
• Improved Airflow parallelism by decomposing tasks and scaling with Kubernetes Executor
• Cross-functional collaboration with quant/data, backend/DevOps, product, and QA to validate strategies and productionize systems
• Able to translate non-technical business needs into ML requirements and deliver usable outputs (visuals + feedback loops)