Tharun Rao

Software Engineer

San Francisco, California, United States2 yrs 9 mos experience

Highly StableAI Enabled

Key Highlights

Expert in developing scalable AI/ML systems.
Improved anomaly resolution times by over 40%.
Passionate about building reliable AI platforms.

Stackforce AI infers this person is a skilled Software Engineer specializing in AI/ML systems for enterprise applications.

Contact

Skills

Core Skills

Large Language Models (llm)Mlops

Other Skills

Multi-agent SystemsRetrieval-Augmented Generation (RAG)Orchestration frameworksAnomaly resolutionHuman-in-the-loop validationPredictive MaintenanceScalable ArchitectureAIOpsJavaScriptReact.jsAngularJSApache SparkRedisMongoDBPostgreSQL

About

I’m an Software Engineer with experience designing and deploying enterprise-grade AI/ML systems that bring together Generative AI, LLM orchestration, and large-scale data engineering.I’ve led the development of multi-agent AI workflows using LLMs, RAG pipelines, and orchestration frameworks to automate complex decision-making in high-volume business systems. These solutions have scaled to handle millions of real-time events daily, improved anomaly resolution times by over 40%, and embedded human-in-the-loop validation to ensure accuracy and compliance.In previous roles, I’ve designed and deployed AIOps and predictive maintenance solutions, achieving high model accuracy and reducing operational downtime through intelligent alerting and event-driven pipelines.I’m passionate about building reliable, secure, and scalable AI platforms, from data retrieval and orchestration to full MLOps deployment, and thrive in fast-paced, high-impact engineering environments.

Experience

2 yrs 9 mos

Total Experience

2 yrs 9 mos

Average Tenure

2 yrs 9 mos

Current Experience

Cisco

Software Engineer

Aug 2023 – Present · 2 yrs 9 mos · United States · Hybrid

I led the development of multi-agent AI workflows using LLMs, RAG pipelines, and orchestration frameworks like Temporal and Orkes to automate complex decision-making across quoting and commerce systems. These solutions processed over 1M+ events daily, improved anomaly resolution speed by 40%, and embedded human-in-the-loop validation for compliance.

Multi-agent SystemsRetrieval-Augmented Generation (RAG)Large Language Models (LLM)Orchestration frameworksAnomaly resolutionHuman-in-the-loop validation+1