# Sarvagya B. > Cisco | Ex-UnitedHealth Group | DTU (DCE) Location: New York, New York, United States Profile: https://flows.cv/sarvagya I’m a Software Engineer specializing in backend infrastructure, cloud-native systems, and applied AI in observability, with hands-on experience in multi-tenant, production-grade deployments. At Cisco, as a Forward Deployed Engineer, I engineered a multi-agent LLM orchestration platform for observability workflows, integrating retrieval-augmented generation (RAG) pipelines combining hybrid semantic and keyword search. I implemented real-time WebSocket services, Thrift-based RPC pipelines, and GraphQL/REST integrations, while optimizing multi-region Kubernetes infrastructure to sustain sub-300ms P95 latency globally. My work spans Kubernetes telemetry, RCA pipelines, and real-time feature flag systems, combining cutting-edge AI with enterprise-grade reliability, security, and multi-tenant isolation. Previously at UnitedHealth Group, I modernized monolithic applications into Spring Boot microservices on Azure Kubernetes Service, built Kafka-based real-time streaming pipelines, migrated databases to Azure CosmosDB, and streamlined CI/CD with Terraform and Jenkins. I also mentored engineers on cloud-native and distributed workflows. During my research in distributed ML and edge computing, I scaled PyTorch training workloads across Kubernetes clusters, built distributed deployment pipelines in Golang/Docker, and developed Prometheus/Grafana/Loki dashboards for cluster observability, improving reliability and monitoring efficiency. I thrive at the intersection of backend infrastructure, cloud-native engineering, and intelligent automation, building systems that scale reliably, simplify operations, and make troubleshooting smarter. I’m passionate about combining observability, AI/LLM experimentation, and production-grade engineering to solve real-world enterprise problems. ## Work Experience ### Forward Deployed Engineer @ Cisco Jan 2024 – Present | New York, United States Owned the design and evolution of a production LLM platform, enabling multi-agent reasoning across infrastructure, logs, and metrics to support observability workflows and incident diagnostics at enterprise scale. Built a cross-signal RCA capability that correlates alerts, application logs, Kubernetes telemetry, and upstream/downstream service behavior to isolate a small set of actionable root causes during large-scale incidents. Introduced deterministic, stateful agent workflows using LangGraph and LangChain, evolving critical paths from controller-driven LLM behavior to explicit execution graphs for improved correctness, debuggability, and reliability. Delivered MCP (Model Context Protocol), a production-grade execution platform for the assistant, enabling IDE-integrated LLM operations and supporting deterministic multi-step agent workflows for safe, reliable, and autonomous AI operations. Led end-to-end multi-region expansion as technical lead, coordinating infrastructure, security, CI/CD, and validation to deliver zero-downtime launches with consistent low-latency performance worldwide. Designed and deployed Retrieval-Augmented Generation (RAG) pipelines over logs, metrics, and internal documentation, grounding LLM responses in live telemetry for accurate operational insights. Designed production rollout safeguards using feature flags, controlled rollbacks, and scoped deployments, enabling safe iteration on high-risk AI features without impacting existing customers. Architected RBAC-aware dynamic prompt composition, enforcing permission boundaries and runtime capability checks to prevent unauthorized tool execution and improve assistant reliability. Designed a standardized audit logging framework that established consistent logging practices, making failures easier to understand and significantly simplifying debugging and incident analysis for engineers. ### Research Assistant @ San Jose State University Jan 2023 – Jan 2024 | San Jose, California, United States Developed an edge computing platform optimizing distributed ML training. (Funded by Intel Corporation). Transformed model execution from single GPU to a distributed ML hosting platform using Kubernetes, boosting scalability by 40% and reducing deployment complexities by 30%. Enhanced backend infrastructure using Golang and Docker for efficient automatic deployment, cutting debugging time by 50% and improving reliability by 25%, streamlining model deployment. Unified Prometheus, Grafana, Loki into a Next.js dashboard, boosting cluster management efficiency by 40% and enabling a 50% increase in model usage analytics for informed performance enhancements. ### Instructional Student Assistant @ San Jose State University Jan 2023 – Jan 2024 | San Jose, California, United States ### Software Engineer @ UnitedHealth Group Jan 2020 – Jan 2022 | Hyderabad, Telangana, India Implemented a Core Java and PL/SQL-driven monolithic application, responsible for data processing, claims management and report generation. Revamped monolithic codebase to Spring Boot microservice architecture, cutting deployment time by 50% and maintaining 99.9% uptime on Kubernetes over 12 months without unplanned outages. Engineered a robust data pipeline on Databricks with Spark and Scala, resulting in efficient data storage through the creation of Delta tables. Automated code deployment by building Jenkins CI/CD pipelines that deployed latest builds, carried out tests, and logged errors encountered; shortened release cycle by 60%. ### Summer Intern @ Egnify Technologies Pvt Ltd Jan 2019 – Jan 2019 | Hyderabad Area, India Contributed to the development of an educational platform emphasizing analytical insights and student growth. Designed and optimized REST API and GraphQL APIs to enhance data processing efficiency by 20%, catering to diverse use cases and ensuring scalability. Utilized multi-threading to expedite data processing and MongoDB storage, achieving a 30% faster assessment generation and swift report delivery. Utilized React.js to create interactive visualizations from persisted data, providing students actionable insights into their learning progress and assessment performance, leading to a 60% improvement in user engagement. ## Education ### Master's degree in Computer Science San José State University ### Bachelor of Technology (B.Tech.) in Computer Software Engineering Delhi College of Engineering ### Class 12 Ch. Baldev Singh Model School ### Class 10 Bal Bhavan Public School ## Contact & Social - LinkedIn: https://linkedin.com/in/sarvagya-bhargava --- Source: https://flows.cv/sarvagya JSON Resume: https://flows.cv/sarvagya/resume.json Last updated: 2026-04-05