Aman Jain · SWE III, AI/ML at Google

I build AI and ML systems that move real metrics.

Specialised in agentic AI and LLM systems.
Open to select roles, collaborations and a few 1:1 calls.

Aman Jain
Google OpenAI Cars24 KotiLabs Vieu 6sense PyTorch LightGBM Two-tower retrieval HNSW pgvector ClickHouse OPA / Rego OpenSearch Snowflake Redis LoRA fine-tuning A/B testing

Selected work

Career timeline
  1. Cars24, 2024-2025

    Per-user ranking that replaced 25 cohorts

    Everyone in a cohort saw the same ranking of 10,000 cars. I rebuilt it per user, with a cold start for the third of users who had never clicked.

    +16% buyer conversion, under 100ms p99

    Read the deep-dive

    +150%click recall

    12%30%

    Click Recall@50, cohorts to per-user

  2. KotiLabs, 2025-2026

    An agentic trading platform built for SEBI compliance

    Language models only plan. Plans compile to a small DSL and a policy engine decides what runs, so a hallucination can't place a non-compliant order.

    Over 90% of frontier-model calls avoided

    Read the deep-dive

    10×cheaper per query

    $0.10$0.01 beforeafter

    LLM cost per query, with a semantic cache and intent router

  3. Vieu, 2026

    Entity resolution on a live relationship graph

    Matching scraped names to the right person in a 900M-row table, where a wrong match invents a relationship. Tuned to under-resolve rather than mis-resolve.

    250M+ academic records in the co-author pipeline

    Read the deep-dive

    900Mperson nodes

    new name

    A scraped name joins the right node, or none at all

I care about systems that move a metric you can check, and designs where the model can't do anything unsafe, even when it's wrong.

Writing

All writing

Work with me

Details and booking

Kits: interview prep spreadsheets and playbooks

Not sure where to start? Ask me anything.

Hiring, or want to build something together? Get in touch.