Skip to content
Bharat Goel

Resume

The one-page version

I build production LLM systems — prompt architecture, retrieval pipelines, and agentic workflows that hold up outside a demo.

Download PDF

One page, generated from this site’s content on every deploy.

01

Experience

Senior AI Research Engineer, NiCE

Mar 2026 – Present · Sandy, UT

  • Architected a hierarchical agentic retrieval system for enterprise knowledge-base question answering, decomposing complex queries and validating retrieved context before generation to hold accuracy on multi-step procedural content — and caught a retrieval-truncation failure before it reached production.
  • Owned the evaluation design, coaching logic, and live demo for a real-time, low-cost agent-coaching prototype, using statistical analysis to identify the strongest predictor of a poor call outcome and rebuilding the alerting around it without adding false alarms.
  • Ran a pre-registered, falsifiable evaluation of a proposed fix for inconsistent multilingual model behaviour, disproving the leading hypothesis through controlled cross-model testing and redirecting the team to the true root cause before further engineering was spent.
  • Directed the rollout of schema-validated structured outputs across a portfolio of production LLM prompts, then root-caused a platform defect where one output shape silently failed on a single model family.

AI Research Engineer, NiCE

Jul 2025 – Mar 2026 · Salt Lake City, UT

  • Designed and architected an LLM-driven ambiguity detection system, dynamically generating clarifying questions through prompt chaining for precise, context-aware responses.
  • Redesigned the prompt evaluation framework into a scalable, model-agnostic system for benchmarking across multiple LLMs using pytest and DeepEval.
  • Partnered with client teams to reduce LLM hallucinations, applying prompt optimization and retrieval strategies to support a successful, low-risk go-live.

Software Engineer, AI Experience, Verse.ai / AtlasRTX

Apr 2023 – Jul 2025 · Park City, UT

  • Optimized lead qualification through an SMS-based follow-up experience using IBM Watson, Azure Function Apps, and C# .NET — increasing availability threefold.
  • Developed automated services with Azure Logic Apps and Service Bus to ingest, clean, and optimize client data, eliminating manual efforts.
  • Trained NLP models to interpret user intent for price filtering, disambiguating based on input context.

Engineering Associate, Goldman Sachs

Dec 2022 – Mar 2023 · Salt Lake City, UT

  • Led front-end development of a resiliency orchestration app for business continuity, keeping datacenters in compliance with failover times.
  • Built a reporting dashboard using React, TypeScript, Java, and MongoDB, delivering audit data in one-third of the previous time.

Senior Engineering Analyst, Goldman Sachs

Jun 2020 – Dec 2022 · Salt Lake City, UT

  • Migrated tax documentation apps from Angular to React/Spring for 300K+ clients globally, improving performance 30–40%.
  • Designed a drag-and-drop PDF tax reporting app using React, TypeScript, Java, SybaseIQ, and DB2, reducing the error rate to ~5%.
02

Skills

AI & ML

LLM Architecture · Prompt Engineering · Prompt Chaining · RAG · Agentic Retrieval · Agentic Workflows · Structured Outputs · NLP Pipelines · IBM Watson · Anthropic Claude · Claude Code

Evaluation & Testing

Evaluation Design · DeepEval · Statistical Analysis · pytest · Cypress · JUnit · Vitest

Backend

Python · Java · Spring Boot · C# .NET · Node.js

Frontend

React · TypeScript · Next.js · Tailwind CSS · AngularJS

Cloud & Infrastructure

Azure Function Apps · Azure Logic Apps · Azure Service Bus · CI/CD

Data

MongoDB · SybaseIQ · DB2

03

Education & awards

  • Master of Science, Software Engineering

    Arizona State University · 2018 – 2020

  • Bachelor of Technology (Honours), Computer Science

    APJ Abdul Kalam Technological University · 2014 – 2018

  • Engineering Graduate Fellowship, SUN Award