applied ai engineer º india · open to remote
i'm an applied ai engineer who builds agentic and rag systems end to end. langgraph pipelines, hybrid retrieval over pgvector, and the eval harnesses that prove they actually work. what i ship is deployed and publicly demoable. i publish the numbers that didn't go my way alongside the ones that did. see my work or reach me at prayagtushar.dev@gmail.com.
blog
work
- metquay inc · software engineerjune 2025 - present
built the async layer of the platform's mcp server, the part that lets ai assistants call its rest api. handles authentication, retries and region routing, and writes error responses a machine can act on, so an agent recovers from a failure without a person.
- zerone consulting · software development internjan 2025 - may 2025
implemented secure sign-in and role-based permissions on a tuition-management platform: three roles, each with its own views and actions.
- collab junction · application developerjune 2024 - aug 2024
improved platform stability with better error messaging and logging, which cut application crashes by 30%.
projects
agent canvas
08.2026A desktop canvas where several AI coding CLIs run as real processes and work as one team.
tauri 2rustmcp
ai ticket triage
08.2026A LangGraph agent that drafts a reply to every support ticket and decides who sees it.
langgraphagentic aifastapi
startupindex
07.2026A hand-rolled RAG system over 116 Indian startups, and the eval harness that decided which retrieval strategy shipped.
ragpgvectorhybrid search
werewolf agents
06.2026A social deduction game where LLM agents lie, deduce and vote each other out on a local model.
multi-agentollamastructured output
github activity
1001 contributions in the last year