Selected work

Selected work. Real teams.

A few projects we've shipped with forward-thinking teams. We can only share what's public; the most interesting work usually isn't.

CrestCard·Fintech

AI-powered spend management at scale

CrestCard needed to categorise millions of transactions and reconcile in real time. We shipped an LLM-powered categoriser with eval-driven guardrails.

GenAIMLOpsFintech
FreshDrop·E-commerce

Demand forecasting that respects reality

Replaced a brittle forecasting stack with a deep-learning pipeline tuned to local demand spikes. Less waste, fewer stockouts, calmer ops teams.

MLData engE-commerce
Ledgerly·SaaS

Expense automation with OCR + LLM

We replaced a queue of manual reviewers with a multi-modal pipeline that reads receipts, infers policy and writes audit trails, with humans in the loop where it matters.

VisionLLMWorkflow
TalentStack·Talent Marketplace

Candidate–role matching at marketplace scale

Built a recommender that surfaces high-fit candidates for open roles and vice versa, with explanations a recruiter can defend.

RecommendersSearch
Start · 08

Tell us about
one task.

One repeated task is enough to start. We reply within one business day, and the form tells you the next step that usually fits.

Start with who you are

Please do not include patient records, client files, identity documents, passwords or credentials. We never need them to start.

Which AI assistants you use
More detail (optional)
We reply within one business day.