Bandla Sai Giridhar

About

Backend engineer who built a Python/Flask system for high-volume healthcare claims processing, using PostgreSQL as the source of truth and RabbitMQ workers for scalable async processing. Experienced in SQLAlchemy/Postgres performance tuning, multi-tenant data isolation (including Postgres RLS), and integrating/versioning ML model services (scikit-learn/PyTorch/Hugging Face) with controlled rollouts. Drove measurable performance gains by batching background jobs and adding Redis caching (40% less workload; response times cut from ~10s to 2–3s).

Experience

Education

Key Strengths

• Designed high-throughput Flask API with heavy processing offloaded to RabbitMQ workers
• Data consistency pattern using DB as source of truth with status transitions and id-based messaging
• SQLAlchemy/PostgreSQL performance tuning (indexes, composite keys, joinedload to avoid N+1)
• Kept APIs fast at scale via pagination, selective column loading, and precomputed summaries
• Integrated ML model services (scikit-learn/PyTorch/Hugging Face) behind REST APIs with prediction logging for monitoring and A/B tests
• Model/version rollout strategy using Git + artifact versioning, v1/v2 endpoints, health checks, and controlled traffic switching
• Multi-tenant data isolation using tenant_id filters, PostgreSQL RLS, and schema/DB-per-tenant when needed
• Improved background processing throughput by batching/scheduling jobs and adding Redis caching (40% workload reduction; latency 10s to 2–3s)