Ramya Sree Kanijam

About

Built and owned an end-to-end AI-driven content enrichment pipeline for a news workflow, using n8n, LLM agents, and external APIs to automate ingestion, deduplication, categorization, and approval routing. Stands out for production-minded AI systems work: they improved reliability with schema validation, retries, idempotency, and monitoring, while automating 90% of processing and cutting duplication errors by 95%+.

Key Strengths

• owned end-to-end AI content deployment from discovery through post-launch stabilization
• built production LLM/agent workflows with tool use and structured outputs
• strong integration and stakeholder coordination across frontend, backend, and approval systems
• improved pipeline reliability with schema validation, fallback handling, and monitoring
• automated 90% of content processing tasks
• reduced duplication errors by over 95%
• designed scalable approval-based content operations with minimal human intervention
• handled messy document inputs with validation, transformation, and low-confidence review flows
• Built and deployed production LLM RAG search over 50k+ internal technical documents
• Achieved ~300ms p95 end-to-end latency at scale (~50 active users) via profiling, batching, parallelization, and ECS warm starts
• Hallucination reduction using retrieval-first design, similarity thresholds, and citation/"I don't know" prompting
• Production-grade testing approach (unit/integration/E2E) with ~75% coverage
• Strong observability and reliability practices (Grafana/Prometheus monitoring, regression detection)
• Cost optimization (prompt caching) reducing LLM API costs by ~20% while maintaining quality
• Data-driven iteration using offline evals and production metrics (latency, confidence, error rates, user feedback) including A/B tests
• Effective collaboration with non-technical stakeholders using demos and metrics to translate needs into requirements
• Designed and owned end-to-end perception-to-decision backend pipeline for robotics
• Reliability engineering for noisy/real-world sensor edge cases (validation, buffering, timestamp alignment)
• Built deterministic debugging workflows using structured logging and replayable tests (e.g., rosbag-style)
• Systematic real-time debugging: reproduced issues from logs, validated TF timing, profiled latency, tuned loop rates and dropped stale frames
• Strong integration focus across distributed/heterogeneous robotic components with strict interfaces and failure-safe behavior

Experience

Education

Skills

Languages

Certifications