Chaitanya Prasad Reddy Narala

About

Senior AI/ML engineer focused on production LLM systems, combining RAG, fine-tuning, distributed training, and AI safety to ship scalable real-time moderation and conversational AI platforms. Stands out for pairing deep AWS/Kubernetes MLOps expertise with measurable impact: 40% lower latency/cost, 30-50% fewer hallucinations, and major reliability gains through observability and automation.

Key Strengths

• End-to-end ownership of production LLM/AI systems from data curation through deployment and monitoring
• Strong MLOps and cloud infrastructure expertise on AWS EKS/Kubernetes for scalable real-time AI serving
• Demonstrated latency and cost optimization, reducing both by 40%
• Deep AI safety focus including guardrails, red teaming, prompt injection and adversarial misuse detection
• RAG and fine-tuning expertise using FAISS, LoRA, and PEFT to improve grounded response quality
• Reduced hallucinations by 30-50% through evaluation pipelines and grounded LLM design
• Production-minded iteration using Kafka feedback loops, active learning, and human-in-the-loop workflows
• Python service design with strong testing discipline across unit, integration, and API contract tests
• Operational reliability improvements, cutting MTTR from about 2 hours to under 45 minutes
• Monitoring automation that reduced incident detection time from hours to under 5 minutes

Experience

Education

Skills

Languages