Bharath Muthyam

About

Built a production LLM-powered workflow at Frontier to extract structured signals from messy, high-volume documents and route work to the right teams, replacing a multi-day, error-prone manual process. Emphasizes production reliability with schema/consistency validation, re-prompting and deterministic fallbacks, plus async pipeline optimizations for predictable latency. Experienced with multi-agent orchestration (LangGraph, AutoGen, CrewAI) and AWS workflow tooling (Step Functions, SQS, Lambda), and delivered ~70% safe automation via stakeholder-driven thresholds and human review.

Experience

Education

Key Strengths

• Built and deployed production LLM workflow automating high-volume document processing and routing
• Reliability engineering for LLM systems via strict validation layers, schema checks, and fallback strategies
• Performance optimization through async workers, batching/caching, rate-limit-aware scheduling, retries, and idempotency
• Strong agent/workflow design with contracts, guardrails, and measurable failure modes
• Rigorous testing approach using golden datasets, regression suites, edge-case and adversarial simulations
• Data-driven evaluation/monitoring of agent chains (step-level success, latency, retries, drift, hallucinations)
• Effective collaboration with non-technical stakeholders; translated needs into metrics and human-in-the-loop review
• Delivered measurable automation impact (automated ~70% of cases with safe routing for low-confidence outputs)