Applied AI · Search & Retrieval · Math · Travel

Hi folks, thanks for dropping by. I’m Antaripa, 26 years young, remote-first, and happiest in my world of code and travel.

I work as an AI Consultant and Technical DevRel partnering with early-stage teams to bring AI native products to life and to the people. My domains span across LLM systems, search, retrieval + eval pipelines, and memory systems.

I love experimenting, explaining, writing technical deep-dives, and building. I’m especially drawn to search and retrieval as a problem space, and it is the domain I enjoy exploring the most. I also do a lots of math in my free-time ;)
If you’re into intelligent systems and the future of developer tooling, you’ll probably feel at home here.

Consulted Tavily, QuotientAI, SpecStory, Tensorlake, Mem0, Agno, and more. Previously led NLP/Search at SproutsAI + Cimba.ai.

How I work

Deeply embedded with the founding team, participating in discussions and hands-on implementation.

  • Pairing research notebooks with shipping code
  • Keeping founders close to the data while I iterate
  • Prioritizing docs + playbooks so teams stay unblocked

Currently in focus

  • Search and Retrieval systems
  • Coding agents and eval pipelines
  • Memory + personalization layers
  • LLM + agent safety tooling
  • Infra that scales from demo to prod

Outside work

Travel is what keeps me going, photography brings joys, and my family keeps me grounded. If I’m not working on something, then I’m probably building a lego set or playing cricket with my brother.

Sitcom comfort loop: Friends, Modern Family, The Big Bang Theory, Brooklyn 99, Young Sheldon, The Good Doctor.

Companies & Clients

SpecStory

Intent layer + applied research

Tavily

Search and agent routing

Quotient AI

Eval + observability

Tensorlake

Data pipelines

Mem0

Memory systems

Hexo AI

Agentic AI for Science

Agno

Multi-agent orchestration

Sagacious

Retrieval stack

Grappus

Agentic workflows

Luppa AI

Content evals

Let’s build

Need someone to architect retrieval, build LLM systems, and write the evals pipeline? Bring me in for focused sprints or long-haul collaborations.