Experience
AI Engineer, Edgeverve Systems, Bangalore
- •Co-authored AI4UI, a multi-agent framework for automated UI generation published on arXiv, covering agent orchestration, tool calling, context management, sandboxed execution, and automated evaluation across code quality, security compliance, and compilation success rates. paper
- •Built RAG pipelines covering document ingestion, semantic chunking, metadata extraction, embedding generation, indexing, hybrid retrieval, and reranking, improving retrieval quality by 40% (Recall@K, Precision@K, MRR, NDCG).
- •Developed agentic workflows with autonomous planning, dynamic tool selection, parallel tool execution, state management, retries, timeouts, and sandboxed execution, reaching a 95% task success rate and 40% lower execution latency.
- •Hands-on with prompt engineering, LangChain, LangGraph, Claude Agent SDK, and agent observability via OpenTelemetry.
- •Owned integration and production debugging across REST APIs, async workflows, Kafka-based messaging, PostgreSQL, and AWS deployments.
- •Mentored 3+ interns on production AI engineering, including coding standards, deployment workflows, and how to not push directly to prod on a Friday.
Projects
CCUDALLMsInferencingSystemsFlashAttention
C/CUDA inference engine with Paged KV Cache, Speculative Decoding, cBLAS/cuBLAS, Batching, FlashAttention, CUDA Graphs, and systems-level optimizations.
AgentsMCPTool CallingFastAPINext.jsOrchestration
FastAPI + MCP financial agent with autonomous orchestration and client-side tool calling with Next.js frontend, built for the Google Hackathon.
GoOpen SourceSecurityREST APIsRuntime Stability
Active contributor to a self-hosted Git platform with 55,000+ GitHub stars, working on security, API design, and runtime stability. (Yes, I fix bugs in software that runs your company's Git server.)
GogRPCHTTP/2NetworkingConcurrencyOpen Source
Refactored bidirectional stream state management in the HTTP/2 transport layer, eliminating redundancy across shared state transitions.
AIAutomationSystem DesignRakuten Conference
Presented X-Cortex, a digital automation engine, to 1,000+ professionals at the Rakuten Conference. Automating day-to-day digital interactions.
PythonPyTorchLLM InferenceQuantizationModel Compression
Optimized LLMs for edge devices using dynamic pruning, quantization, and distributed inference by making models fit where they shouldn't.
PythonOpen SourceCode FormatterPython 3.12CompilerAST
Contributed a fix to Black, the uncompromising Python code formatter, resolving formatting issues with Python 3.12's new generics syntax. The fix ensures proper handling of type parameters when function parameters contain trailing commas.
GoLSPLanguage Server ProtocolCUDACompilerIncremental Parsing
A blazing-fast Language Server Protocol (LSP) implementation in Go for CUDA development, featuring incremental diffing, intelligent hover documentation, and context-aware autocompletion built from scratch.
PythonGANMachine LearningPytorch
A GAN-based data anonymization system that preserves data utility while removing sensitive information. Won 2nd place in AI domain at hackathon.
SvelteTypeScriptTailwindCSSLogisticsPytorch
A logistics platform that simplifies international shipping tracking and management. Won 1st place in Logistics domain at Hackfest 2024.
SvelteTypeScriptTailwindCSSUI/UX
An immersive treasure hunt game with a Windows boot menu-inspired interface, created for Incridea college event.
Next.jsTypeScriptTailwindCSSReact
Frontend development for Incridea, the largest college event platform, as part of the core technical team.
Next.jsPostgresGoogle Maps API
A comprehensive platform for student resource management and collaboration.
Next.jsReactTailwindCSSTypeScript
A minimal and modern portfolio website showcasing projects and skills.
Skills
Python
LangChain / LangGraph
PyTorch
Agents & RAG
FastAPI
Postgres
REST APIs
Kafka
Distributed Systems
Microservices
Async Programming
Go
AWS
Docker
Redis
CUDA / C
TypeScript
Git
LeetCode
Education
B.E. in Artificial Intelligence and Machine Learning, NMAMIT, Nitte
CGPA: 9.41 / 10. Relevant coursework: Data Structures, Algorithms, OS, Machine Learning, GenAI, DBMS, Cloud.
Contact Me
Forms TODO! I will soon add a section for anonymous reach outs!
These are my preferred ways of contact. Although you can message me on any of the socials I have mentioned!