Praneeth Ravuri

AI Engineer at

Tuskira

Building Agentic AI and Scalable Systems for Cybersecurity.

GitHub LinkedIn X Resume

San Francisco, USA

PythonGoTypeScriptReactAWSGCPKubernetesDockerPostgreSQLMongoDBRedisNeo4j

Experience

Dec 2025 - Present

AI Engineer at

Tuskira

Building autonomous AI agents for cybersecurity investigations that query multiple data sources and maintain context across long sessions. Designed a memory layer separating long-term knowledge from active reasoning to prevent context drift, storing summarized investigations in Neo4j and Pinecone for retrieval. Optimized MCP servers in Go and Python to filter data before LLM processing, reducing token usage while maintaining response consistency. Deployed on AWS with Kubernetes for continuous operation across multiple client environments.

Agentic AIMCPPythonGoAWSKubernetesPostgreSQLNeo4jPinecone

Oct 2024 - Nov 2025

Software Engineer at

Lumen

Built backend services processing millions of network flows per minute for traffic analysis platform. Architected event-driven pipeline with Kafka to decouple ingestion from processing, preventing bottlenecks from cascading failures. Implemented backpressure handling in Go using buffered channels to absorb traffic spikes and balanced partition consumption to maintain throughput during peak periods. Deployed with Docker and Kubernetes, achieving zero data loss across all production deployments.

GoKafkaMongoDBDockerKubernetes

Jan 2022 - Jun 2022

Full Stack Engineer Intern at

ADP

Modernized legacy employee portal handling thousands of daily users. Built React frontend and optimized Node.js backend with Redis caching layer to reduce repeated database queries. Improved response times and stabilized performance during peak traffic periods.

ReactNode.jsRedisJavaScript

Projects

Gary

Crew AIMongoDBGCP

AI agent that rewrites resumes to match job descriptions without keyword stuffing. Built multi-step workflow with Crew AI that extracts role requirements, analyzes tone, and rewrites experience while maintaining narrative consistency. Outputs tailored PDF/Word docs that pass ATS filters. Deployed on GCP with MongoDB for resume version management.

Pitstop

FastMCPHttpX

MCP server connecting live F1 telemetry to LLMs for natural language race queries. Processes high-frequency data streams with FastMCP and HttpX, filtering noise to extract meaningful signals like lap times, tire degradation, and pit windows. Enables conversational queries about race strategy and pace without switching dashboards.

Smart Traffic

NumPyPygameMatplotlib

Reinforcement learning simulation using SARSA to optimize traffic light timing based on real-time queue lengths. Modeled intersection dynamics with NumPy and Pygame, training agent to learn adaptive switching policies instead of fixed schedules. Reduced average wait times compared to static timers, demonstrating RL for real-time decision-making systems.

Notstuck

ReactNext.jsPostgreSQLPineconeCrew AI

Hybrid search RAG system combining vector similarity and keyword filtering for technical documentation retrieval. Built with Next.js and React frontend, PostgreSQL for metadata, and Pinecone for vector search. Crew AI generates answers with citations, balancing semantic understanding with exact term matching to reduce time spent manually searching PDFs.

Education

George Mason University

Master’s in Computer Science

GRIET

Bachelor’s in Computer Science