Eudexia — An LLM-based AI Assistant
A RAG assistant that lets teams query their own private documentation in plain language and get answers grounded in real sources — collapsing a 30-minute hunt across hundreds of internal docs into under a minute.
Aakash Agrawal
Building the platforms & infrastructure AI runs on
About
I work in the unglamorous middle layer of AI, turning research and prototypes into systems teams can depend on. 0→1 is my default: ML platforms, agentic and GenAI infrastructure, and the whole path to production.
The part I love is the bridge - making research-stage ideas hold up and scale, including the bits people skip: governance, cost, adoption.
Outside that: a bike, a race, travel, or a new language (not the programming kind :-)).
Experience
2022 — Now 
Member of Scientific Staff · DISH Network · United States
Building ML/AI platforms and agentic + GenAI infrastructure: from RL-driven self-optimizing 5G networks to an enterprise Data & AI platform.
2020 — 2022 
Senior Data Scientist · Oracle · Broomfield, CO
Audience-modeling R&D for Advertising Cloud: end-to-end ML for ad targeting at scale.
2019 — 2020 
Data Science Associate · Mu Sigma · Bellevue, WA
Data science for T-Mobile: NLP call-driver classification and BI analytics pipelines.
2017 — 2019 
MS, Information Management · University of Washington · Seattle, WA
Master's in Data Science & Business Intelligence. TA for ML & econometrics (IMT 574).
2015 — 2017 
Assistant Systems Engineer · Tata Consultancy Services · Bengaluru, India
R&D in image processing and augmented / mixed-reality applications.
Writing
— A three-part series on building a self-perfecting 5G network —
Network Observability Framework
The data layer underneath: an open-source, cloud-agnostic observability stack (Prometheus, Thanos, Loki) that collects logs and metrics from a Kubernetes cluster and feeds them to the RL agent in near real time.
Self-Perfecting Networks
How a reinforcement-learning agent can act as the brain of a 5G network that tunes itself — a closed-loop system where the agent observes a simulated 5G core running as a Kubernetes app and adjusts resources to balance service quality against cost.
Open Source Machine Learning Architecture for Telco
A modular, open-source ML framework spanning the full lifecycle — ingestion, data prep, training, deployment — built so teams can swap compute backends without re-plumbing. Applied to anomaly detection on Kubernetes performance logs.
Open Source
Projects & Demos
Edge Agent Ops
A guardrailed LLM agent that monitors a fleet of edge AI inference nodes, diagnoses faults, and remediates them only within hard policy limits. Ships an evaluation harness and a live Prometheus + Grafana observability stack.
LLM Serving Stack
An OpenAI-compatible LLM inference gateway — async request queue, SSE streaming, auth, rate limiting, prompt-based routing, OpenTelemetry tracing, and a provisioned Prometheus/Grafana board. Ollama-backed locally, swappable to vLLM/TGI.
Patents
- Pattern Detection in a Cellular Telecommunication Network US 18/418,011 Allowed
- End-to-End Package Deployment System for Cloud-Native Networks US 18/915,123 Pending
- Self-Optimizing Networks US 19/343,356 Pending