Harshit P.Private profile: Upwork shows its earnings only to signed-in members, so we check it every few weeks, not daily. MRR here is a rough estimate (Upwork's six-month earnings ÷ months active). Last read Nov 5, 2026.

I help teams turn business problems into working AI systems, data pipelines, and software. I work in a Forward Deployed Engineering style: understand your workflow, define the right solution, build and integrate it, and iterate with the people who use it. My focus areas: • AI agents and agentic workflows: tool use, orchestration, knowledge assistants, RAG and GraphRAG, and business process automation. • Voice agents and conversational AI: voice-enabled experiences, transcription workflows, and integration with backend services. • Data pipelines: multi-source ingestion, ETL, data validation, feature engineering, and analytics-ready datasets. • Software development: Python/FastAPI backends, APIs, databases, React/Next.js applications, and AI-powered internal tools and SaaS products. • Reliable AI delivery: evaluation, guardrails, model optimization, deployment, and practical cost and latency improvements. My background spans AI and software engineering at Emmes Group (Veridix AI), Samsung Research Institute, and Accenture. My work includes private language-model systems, multi-LoRA inference, LLM evaluation, GraphRAG, multimodal agents, on-device AI, and data infrastructure. My projects include MeetEasy, a relationship-intelligence and meeting-preparation prototype, and MindSpace, an AI advisory workspace with specialist personas and multi-persona council orchestration. Core tools include Python, SQL, FastAPI, React, Next.js, TypeScript, PyTorch, TensorFlow, LangGraph, Neo4j, and AWS. I can work with you from discovery and architecture through implementation, integration, and deployment. Share the workflow you want to improve, the systems it needs to connect to, and what a successful result looks like.