Founding AI Engineer

Meraki Labs; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Meraki Labs in Bengaluru, India, seeks a production‑grade engineer to own end‑to‑end retrieval for Proofline, from ingestion to retrieval quality, collaborating with founders on AI‑first products.

You will build and maintain a high‑velocity RAG/search pipeline using Python, embeddings, vector stores, and possibly graph databases, with a focus on measurable improvements in retrieval accuracy and latency.

Qualifications

• 7+ years of experience in ML/backend engineering.
• Production RAG, search, or IR systems experience.
• Strong Python; hands-on with embeddings, vector stores, and rerankers.
• Graph databases a plus.
• Demonstrated evaluation rigour: show how retrieval quality was measured and improved.

Responsibilities

• Own the retrieval pipeline: document ingestion, chunking, embeddings, hybrid search, reranking.
• Build dual-corpus retrieval across published literature and private institutional documents, with provenance.
• Build citation and identifier resolution (DOI/arXiv-class) and large-corpus onboarding.
• Own retrieval evaluation: build the harness, set the metrics, prove improvement release over release.

Skills

Python

Embeddings

Vector stores

RAG/IR systems

Distributed systems

Tools

Graph databases

Job description

Meraki Labs (founded by Mukesh Bansal & Peeyush Ranjan) builds and rapidly scales AI-first, "moonshot" startups. We're looking for a high-velocity, production-grade engineer to build 0-to-1 products alongside founders.

About the role

Proofline is live in production with institutional pilots underway. This role owns the capability end-to-end, from ingestion to retrieval quality, connecting across multiple sources of information for research institutions and enterprise research teams.

Responsibilities

• Own the retrieval pipeline: document ingestion, chunking, embeddings, hybrid search, reranking.
• Build dual-corpus retrieval across published literature and private institutional documents, with provenance.
• Build citation and identifier resolution (DOI/arXiv-class) and large-corpus onboarding.
• Own retrieval evaluation: build the harness, set the metrics, prove improvement release over release.

Requirements

• Experience - 7+ years.
• ML/backend engineering with production RAG, search, or IR systems experience.
• Strong Python; hands-on with embeddings, vector stores, and rerankers; graph databases a plus.
• Demonstrated evaluation rigour: you can show how you measured and improved retrieval quality.
• Comfort with scientific or technical document corpora is a plus.

How We Work

Small team, high trust, written decisions. Designs get adversarial review before code; PRs get automated review driven to zero open findings; features aren't done until verified on a live system. AI agents do a large share of the implementation—your leverage is judgment: framing the problem, freezing the right design, and knowing when the machine is wrong.

You Should Apply If

• You enjoy turning messy problems into concrete solutions.
• You thrive in fast-moving, low-process environments.
• You're excited about production engineering (monitoring, reliability, cost, latency).

You Should Not Apply If

• You want remote/hybrid (this is onsite Bangalore only).
• You prefer narrow tickets and minimal ambiguity.
• You prefer highly structured, slow-moving product organizations.