Now2 roles

Evidane
Founder2026 — presentConcurrent with Brekfuz
Founded and shipped evidence-backed legal AI: 1,000+ signups, paying customers, and five US law firms working with it.
- Merged two legal-AI codebases into one product and shipped v1.0.
- Built everything a paying customer touches: auth, Stripe credits and billing with replay-safe checkout, the Postgres path, hosting, the rebrand and the launch. 1,000+ commits in fifteen weeks.
- Shipped a product where 87 specialist agents, ten verification passes and a lawyer's sign-off stand behind every finding.
Founding and launch / Billing, auth and hosting

Brekfuz
Founding EngineerFeb 2026 — present · Full-time · Remote
Built the AI agent platform, then Breken, its second product. Backed by Pareto Holdings, Pear VC, Z Fellows, Cory Levy and Collective Global.
- Shipped four production services on AWS (web, API, a worker fleet and a Go memory service) that served 213,761 requests in fourteen days, over twelve Redis stream queues with fair per-tenant admission.
- Built the memory agents that extract, consolidate and recall what a company knows. They have served 100,000+ requests, behind row-level security forced on 103 tables that the services verify at boot.
- Engineered Breken's code intelligence, renderer and sandbox. It finds a bug, proves it and opens the fix: 54 merged upstream across 34 repositories, at Langflow, Tailscale, Unsloth and Twenty.
Agent platform and infrastructure / Self-healing code
Previously1 role

Hey Amara
Founding AI EngineerJul 2025 — Jul 2026 · Full-time · RemoteConcurrent with Brekfuz from Feb 2026
Built the backend and AI infrastructure of a multi-tenant agent platform for recruitment agencies, as its founding engineering hire.
- Moved the platform's message queues off Redis and onto RabbitMQ, and rebuilt every path through them — circuit breaker, API gateway, orchestrator and service launcher — so one slow agent can no longer hold a caller open.
- Built the email generation subsystem: a composition service and a generation orchestrator over vector retrieval from four sources, including recruiter memory and prior communications.
- Built the compaction that keeps a long conversation inside its token budget by summarising into a validated schema instead of free text, plus the auth middleware and the integration test suite around it.
Queue and messaging infrastructure / Retrieval and generation pipelines
Earlier3 roles
UltraSafe AI, experience page
Applied AI Engineer · Internship
Mar 2025 — Jul 2025
Built a medical retrieval system for regulated clinical documents, from PDF extraction to a deployed service.
Munshot, experience page
Founding AI Engineer · Internship
Jan 2025 — Mar 2025
Built an AI agent for institutional financial research, from its tool layer to the API that served it.
RealAIzation, experience page
AI Engineer · Internship
Oct 2024 — Dec 2024
Built the AI layer of a talent platform that ran the whole hiring loop, from the job description to the candidate.
Before engineering: product at HappyAspirants, brand at Springoo and sponsorship at The E-Cell, LNMIIT (2023–2024).