2025–2026Role period
Industry work
Voice AI in production
Engineering a healthcare voice agent with real-time scheduling integrations.
Alex Chandler AI scientist & engineer
Research. Engineering.
AI evaluation.
Education & experience.
Explore experience ↗Aug 2025–Present
BCG
Voice AI, evaluation, and enterprise systems.
Explore work ↗Jul 2024–Jul 2025Deloitte
Factuality assessment, retrieval and enterprise AI infrastructure.
Explore work ↗Jun–Aug 2023Fidelity
Financial language systems and automatic evaluation.
Explore work ↗Oct 2020–Mar 2022Keysight
Software engineering for network visibility products.
Explore work ↗2019–2024UT Austin
A foundation in computer science, artificial intelligence and machine learning.
Explore work ↗The full body of work
Research. Engineering.
Through the years.
Explore 23 projects, publications and engineering contributions, from current work to the earliest experiments.
Through the years
Ongoing2026
2025–2026Role period
Industry work
Voice-agent simulation and evaluation
A simulation harness for realistic caller personas, automated scoring and behavioral regression tests.
2026Ongoing research
Interactive research
What counts as a hallucination?
Explore 54 terms, their working definitions, and the boundaries between them.
October2025
2025Publication
Patent application
Measuring the performance of large language models
Systems and methods for measuring performance of large language models.
July2025
2024–2025Role period
Industry work
LLM report assessment
Assessment, verification and correction workflows for generated reports.
2024–2025Role period
Industry work
Retrieval and citations
Hybrid retrieval, query transformation and citation generation for enterprise AI.
February2025
2025Manuscript
Model, dataset & draft
Fine-tuning LLMs for batch prompting
Fine-tuned language models that answer batches of questions in one inference pass.
2025
2025Publication
FinNLP 2025
Financial misinformation detection
Instruction-tuning for financial claim classification and reasoned explanations.
2025Publication
SemEval 2025
Finding hallucinations across languages
Token-level detection of hallucinated spans using features from internal LLM layers.
April2024
2024Repository
Research project
Mastering Leduc Hold’em
Comparing reinforcement learning and counterfactual regret minimization in imperfect-information poker.
2024
2024Publication
EMNLP 2024
Detecting factual errors with DEEP
Ensembling prompt judgments to detect factual inconsistencies in generated summaries.
December2023
2023Manuscript
Research project
Factuality detection with AlignScore and LLMs
Context decomposition and prompt-based evaluation of factual consistency.
November2023
2023Repository
September2023
2023Repository
Zero-shot & multi-task
Shared context. Multiple answers.
Give a language model one document and several questions or requested outputs. Return the answers together in one inference pass.
August2023
2023Role period
Industry work
Financial language systems
Named-entity recognition, table extraction and automatic evaluation for financial question answering.
April2023
2023Manuscript
Research project
Temporal grounding in egocentric video
Contrastive learning, hard negatives and temporal reordering for video-language representations.
November2022
2022Repository
Reinforcement Learning 2022
Learning from mixed-quality demonstrations
Reformulating robot imitation learning as a sequence of returns, states, and actions.
September2022
2022Repository
Research project
Zero-shot controllable text generation
Topical control through contrasting expert language models and self-organizing structures.
March2022
2020–2022Role period
Industry work
Network visibility engineering
APIs, test automation and AI threat detection for network visibility products.
November2021
2021Repository
Research project
Adversarial attacks on question answering
Modified beam search for adversarial triggers against ELECTRA question answering.
August2020
2020Repository
Independent project
Learning the musical-instrument market
Instrument identification, market analysis and a database of more than 10,000 instruments.
May2020
2019–2020Research period
Research project
Deep reinforcement learning for wells
Planning well paths through 3D subsurface data with actor-critic methods.
July2018
2018Publication
Research & engineering
Gerrymandering, graphs and geometry
Analyzing political districts with computational geometry, networks and a web application.
Publications
& intellectual property.
Google Scholar ↗EMNLP 2024
Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors
Explore ↗RL 2022Decision Transformer for Robot Imitation Learning
Explore ↗FinNLP 2025Deloitte (Drocks) at the Financial Misinformation Detection Challenge Task: Enhancing Misinformation Detection through Instruction-Tuned Models
Explore ↗SemEval 2025Deloitte (Drocks) at SemEval-2025 Task 3: Fine-Grained Multilingual Hallucination Detection Using Internal LLM Weights
Explore ↗Patent applicationSystems and methods for measuring performance of large language models
Explore ↗Hallucination detection, factuality research,
and the engineering of AI systems.