How I can help
AI agent security review
A fixed-scope test of an agent that can act: prompt injection, tool misuse, data leaks. Written findings, fixes and a retest.
Voice agent architecture review
Latency budget, speech recognition and synthesis choices, cost per minute and evaluation on your real audio.
Due diligence and advisory
Technical due diligence on AI startups for investors, and fractional CTO support for teams building on AI.
Recent work, anonymized: cut a production voice agent's response latency from 3.2 s to under 800 ms ahead of an enterprise launch. How engagements work →
Free resource: the voice agent review checklist I use, covering latency, recognition, cost, evaluation and security.
Start here
The posts I would hand a CTO or founder first.
When self-hosted TTS beats the API: the 2026 cost cliff
A worked cost model for when running your own speech synthesis beats paying per character.
Why human-in-the-loop beats full autonomy for high-stakes agent actions
The reliability math behind putting a human approval step into high-stakes agents.
AI security assessments: how to evaluate an LLM system you did not build
How to assess the security of an LLM system you did not build.
ASR is solved (on benchmarks): the real-world gap every voice agent team hits
Why speech recognition benchmark scores overstate how a model will do on your calls.
The build vs buy decision for AI in 2026: a practical framework
A framework for the build-or-buy calls every AI team faces.
How I evaluate AI startups for investors: 8 technical signals
The first-pass technical screen I use before a full due diligence.
Topics
Voice AI
65 articles
Speech recognition, speech synthesis and voice agents: latency, cost and evaluation on real audio.
AI Agents
104 articles
Tool use, memory, multi-agent systems, evaluation and the reliability math of putting agents in production.
AI Security
43 articles
Prompt injection, agent privilege escalation, red teaming and security programs for LLM and voice systems.
ML Systems
80 articles
Serving, inference cost, quantization, KV caches and the build-or-buy decisions behind production ML.
Advisory
2 articles
For founders, CTOs and investors: technical health checks, due diligence and build-or-buy calls.
Research
19 publications, 2 patents
Peer-reviewed work on multilingual speech recognition, speaker personalization and speech synthesis.
Selected research
Speech recognition and synthesis research, much of it on Indian languages. Google Scholar →
A Unified Approach to Multilingual ASR with Improved Language Identification for Indic Languages
INTERSPEECH 2024: Joint language identification and multilingual recognition on Whisper: 19.1% absolute WER improvement on Indic languages.
Speaker Personalization for ASR using Weight-Decomposed Low-Rank Adaptation
INTERSPEECH 2024: LoRA and DoRA adaptation of a conformer transducer: 20% average relative WER reduction for speakers with little data.
Robust Speaker Personalisation Using Generalized Low-Rank Adaptation for ASR
ICASSP 2024: Generalized LoRA for per-speaker adaptation while keeping compute and memory low.
Robust Speech Recognition Using Meta-Learning for Low-Resource Accents
NCC 2024: Model-agnostic meta-learning for accented English: about 12% relative WER improvement on most low-resource accents.
Building or buying an AI agent?
Tell me what you are building and where it hurts. The first call is 30 minutes and free, and I will say plainly if I am not the right person.
Work with me