AI Platform Engineer with 4+ years of experience building enterprise AI platforms, agent orchestration systems, production-grade LLM applications, and cloud-native full-stack products.
I currently work at Storable as a Software Engineer, where I'm designing an enterprise AI SDK built on LangGraph and a custom execution engine to standardize agent orchestration, tool calling, and AI integrations across products. I also architected and shipped a React Native app end to end using an AI-native SDLC, and helped transform a large-scale monolithic platform into distributed services. My core focus is AI platform engineering - multi-agent orchestration, RAG pipelines, memory and long-context management, and tool-calling workflows - building AI-first products that stay reliable in production while still moving fast.
⭐ Building production-grade backend services with Node.js, NestJS, FastAPI, GraphQL, REST, and microservice architecture
⭐ Developing modern frontends with React, Next.js, and React Native for cross-platform experiences
⭐ Shipping products with an AI-native SDLC - AI-assisted implementation, testing, and code review using Claude Code and Cursor
⭐ Designing schema-driven UIs and reusable component systems (Anu.dev) to accelerate product velocity
⭐ Optimizing scalability and reliability through caching, event-driven flows, and clean service boundaries
⭐ Designing AI SDKs and execution engines that standardize agent orchestration and AI integrations across products
⭐ Building multi-agent systems with LangGraph, LangChain, and Temporal for planning, routing, and durable workflow execution
⭐ Implementing RAG pipelines with embeddings, semantic search, metadata filtering, reranking, and vector databases
⭐ Developing tool calling and Model Context Protocol (MCP) integrations for autonomous task execution
⭐ Engineering long-context and memory management, session handling, and context optimization for reliable reasoning
⭐ Improving LLM reliability with prompt engineering, evaluation, guardrails, and Langfuse observability
⭐ Running self-hosted inference with vLLM, Ollama, Gemma, and Qwen - tuning latency, throughput, and GPU utilization
⭐ Deploying and managing distributed services on AWS and Google Cloud
⭐ Building delivery pipelines using Docker, Kubernetes (EKS), and Terraform
⭐ Implementing observability with OpenTelemetry, Grafana, and Prometheus
⭐ Designing event-driven systems with Kafka and MQTT for real-time workloads
⭐ Running production-grade data systems with PostgreSQL, MongoDB, MySQL, and Redis
⭐ Designing highly attractive user interface for mobile and web applications
⭐ Customizing logo designs and building logos from scratch
⭐ Creating the flow of application functionalities to optimize user experience
⭐ Analyzing, modeling and interpreting data with statistical methods
⭐ Building IoT applications with Arduino and Raspberry Pi
⭐ Creating data pipelines and ETL workflows
⭐ Visualizing insights with Power BI and custom dashboards
Built by Nasigari Jitesh