Four companies, two promotions, one through-line: quality you can measure.
AI-native tax research & planning platform; first new entrant to clear IRS e-filing approval alongside incumbents.
Eval loop
Own end-to-end output quality for the production tax-research LLM: a citation-accuracy evaluation loop (flag → classify by failure mode → weekly review) and a four-dimension rubric (answerability, accuracy, citation quality, actionability) that benchmarks model configurations and catches regressions before release — ~95% citation accuracy held on the eval set.
Benchmarking
Built the competitive model-benchmarking program: the platform scored against three competing platforms across 50+ scenarios over 5 rounds; designed a "pipeline-collapse" eval measuring chain coherence and self-QC honesty across a full multi-step tax workflow.
Failure mode
Fixed a systemic "knowledge–citation gap" failure mode — plausible-but-wrong citations, a false-positive problem — by attaching document identity and sub-type to every cited source. Citation precision rose; outputs became traceable and audit-ready.
Latency
Cut workflow latency ~90% (10–15 minutes → under a minute) by scoping incremental edits to changed inputs instead of reprocessing the full document set.
Corpus
Architected and QA’d the 270K+-record RAG corpus across 100+ legal source types: ingestion-pipeline PRDs, MongoDB schemas, a Python fetchability harness across 378 sources, and remediation of ~139K scraped documents.
Research
Led legal-support research across 160+ tax strategies (a Legal Support Matrix built from Tax Court cases, IRS rulings, and audit guidance) and shipped Source Explorer — command-palette search with cross-type related sources.
Global employment platform enabling compliant hiring across 150+ countries.
Owned the Value-Added Services vertical (procurement, BGV, ITSM, partnerships): $100K incremental revenue and a 47% efficiency gain from new SOPs; launched the PosterElite compliance partnership end-to-end in 21 days.
India's leading HR technology platform; $25M+ ARR CoreHR suite.
Built the Background Verification module zero-to-one on the Checkr API — Keka's first US-market product. From nothing to 28 US enterprise clients and $2.7M MRR, it drove the company's first US expansion and was a full course in integration edge cases, compliance constraints, and enterprise onboarding.
Also
6 SSO integrations (Azure AD / Google Workspace) → 27% adoption lift and $121K upsell; led the Exit Module revamp → offboarding time down 28%, CSAT up 80%.
Led agile transformation of LMS development (43% faster delivery); drove 31% growth in customer conversions via an end-to-end video-learning rollout.
Mechanical engineering → enterprise product → AI product quality.
If you're shipping an LLM product, let's talk about what your evals miss.