Anu Kumar — Senior AI Engineer
Senior AI Engineer working on LLM agents, retrieval pipelines, and the infrastructure that keeps them running.
Mohali, Punjab, India · anu2614kumar@gmail.com
Reasoning loops, tool-calling, confidence scoring, and human-approval checkpoints. The interesting problems are not the prompts. They are what happens when a tool call fails at three in the morning, when a model returns something plausible and wrong, and when a decision needs a person to sign off before it executes.
RAG pipelines that tie agent decisions to real company data instead of model memory. Chunking, embedding, ranking, and the evaluation loop that tells you whether retrieval is actually helping.
FastAPI and Node services, PostgreSQL and Redis, Docker and Kubernetes, CI/CD. Models are a component. The system around them is the product.
The agent and LLM layer of an enterprise agentic platform.
Core contributor to the agent runtime: reasoning and tool-calling workflows, confidence scoring on generated output, and human-approval checkpoints before an agent action commits. The retrieval side grounds those decisions in company data rather than model priors.
Python · FastAPI · LLM agents · RAG · Docker · Kubernetes
Multi-tenant SaaS CRM where every customer gets an isolated database and its own process.
Provisioning creates the tenant database, runs industry-specific migrations, starts a dedicated backend process, and writes the DNS record. Feature access is gated per industry and plan, so one codebase serves verticals that do not resemble each other.
Node.js · Express · MariaDB · React · PM2 · Cloudflare
Product and ad-campaign discovery for dropshippers, with an AI-assisted store search.
Full-stack build on React and Node with a FastAPI service alongside it. Integrated the OpenAI realtime API so users could interrogate the catalogue conversationally instead of filtering it.
React · Node.js · PostgreSQL · FastAPI · AWS · OpenAI
An SEO command centre run by a set of specialised agents rather than one prompt.
Separate agents handle audit, keyword research, content briefs, and internal linking, each with its own tools and output contract. Multi-project, so one workspace can hold unrelated sites without the agents bleeding context across them.
Node.js · React · LLM agents · PostgreSQL
A convolutional model that classifies chest X-rays for COVID-19 positivity.
Trained end to end: dataset preparation, augmentation, architecture selection, and evaluation. The early project that made the case for everything after it.
Python · CNN · Computer vision · Deep learning
Multi-tenancy usually means a tenant_id column and a lot of discipline. NapCRM does not work that way. Each customer gets a physically separate database and its own running process, which makes a cross-tenant leak something you cannot write by accident.
Mar 2026 - Present
Designing agent and LLM systems for project intelligence, workflow automation, and decision support. Building RAG pipelines with confidence scoring and human-approval controls, wired into enterprise tools and databases, shipped through Docker, Kubernetes, and CI/CD.
Aug 2023 - Feb 2026
Built full-stack applications on React, Node.js, and PostgreSQL across DigitalOcean and AWS, with REST APIs for real-time data exchange. Engineered an AI-assisted interaction platform on React, FastAPI, the Twilio SDK, and the OpenAI APIs.
2023
Django and React applications with secure backends on the Django ORM, SQLite3, and AWS EC2.
2023
Java applications on JDBC and J2EE, plus SQL query optimisation that cut turnaround on the team's reporting work.
B.Tech, Computer Science and Engineering, I.K.G. Punjab Technical University, 2019 - 2023.
Open to senior AI engineering roles, and to problems where the model is the easy part. The fastest way to reach me is email.