An AI & Backend Systems Engineer specializing in the design and orchestration of multi-agent LLM workflows. The core engineering focus is on replacing single-threaded, blocking LLM calls with asynchronous, queue-based architectures that stay responsive under long-running inference. Expertise lies in system-level orchestration using LangGraph and Google ADK to coordinate specialized AI agents, and structured outputs (Pydantic) to keep multi-step reasoning reliable rather than freeform. Rather than treating AI as a simple chatbot interface, the focus is on using AI as a reasoning layer embedded within decoupled services agents that plan, retrieve, and act across separate frontend, backend, and worker processes. This technical execution includes deploying agent workflows over asynchronous message queues (Redis/BullMQ), maintaining persistent semantic memory through vector databases (Supabase pgvector, Pinecone), and containerizing backend and worker processes (Docker) for deployment across Render, Vercel, and Hugging Face Spaces.
AI & Cloud Engineering Intern
IBM SkillsBuild & Edunet Foundation
- Participated in an intensive, project-based enterprise engineering track focused on emerging cloud platforms and agentic AI architectures under the IBM SkillsBuild initiative.
- Designed and engineered the watsonx-nutrition-agent utilizing IBM Watsonx Orchestrate, implementing structured prompt behavior mapping, runtime knowledge-source ingestion, and automated multi-turn reasoning pipelines tailored for precision advisory domains.
- Explored real-world enterprise agent integration patterns, leveraging cloud-native tools to orchestrate deterministic workflows and minimize hallucination vectors in conversational interfaces.
AI & Automation Engineering Intern
NexLevr
- Engaged in advanced automation engineering workflows, focusing heavily on execution resilience, system integration, and large language model output governance.
- Developed and open-sourced the LLM-Output-Variance-CLI, an auxiliary developer tool engineered to systematically audit temperature parameters, measure probabilistic generation drift, and evaluate token-level variance across high-parameter inference endpoints.
- Focused on bridging production reliability gaps by establishing reproducible measurement scripts for runtime model stability.
Distributed AI Researcher was born out of a simple problem: LLM inference is slow. HTTP has timeouts. Blocking a web request for 30–120 seconds of LLM work causes 504 Gateway Timeouts and a terrible user experience. This system replaces the single-threaded LLM call model with a genuine multi-agent swarm using a fire-and-forget job queue pattern. A LangGraph pipeline coordinates three specialized agents: an Architect that decomposes the query, Scout agents that search the web concurrently, and a Synthesizer that fuses all findings into a professional report.
A benchmarking CLI that systematically evaluates how the temperature parameter affects Large Language Model output ranging from deterministic precision to creative divergence. This project was built as part of the roadmap.sh LLM/OpenAI API Track, demonstrating programmatic LLM interaction beyond the standard ChatGPT interface using the OpenAI-compatible chat.completions API pattern.
B.TECH
MALLA REDDY INSTITUTION OF TECHNOLOGY AND SCIENCE · 8.18
Microsoft
Aug 2026Neo4j GraphAcademy
Oct 2026Oracle Cloud Infrastructure 2026 Certified AI Foundations Associate
Oracle University
Aug 2026
Attendee · Oct 24, 2026