Display

Theme
Motion

Calm pauses moving backgrounds and effects.

Text size

Systems & the playbook.

Deep-dives on the ML systems I've built, an 8-part series on how an AI trading desk works inside, and a free 16-part interview playbook for ML, AI and software engineers.

Series8 parts · 67 min

Inside āagman

The architecture of an AI trading desk, one layer per post: a typed strategy language, agents that can't reach the broker, a deterministic backtester, the data platform, and the gates in front of every order. Real trade-offs, written for engineers.

  • 8parts
  • 5worker agents
  • 4risk gates
  • 90%+LLM calls avoided
  • 10×screener throughput
  1. IThe map11 min
  2. IIThinking14 min
  3. IIIEvidence24 min
  4. IVExecution18 min
Series16 parts · about 2.5 hours

The interview playbook

Written to help you through your own search: how to get interviews, how to prepare, what each round is like, what rejections teach, and how to choose between offers. Process and preparation, not interview questions. Each part is 9 to 12 minutes and stands on its own. Free, and it stays free.

  • 35companies
  • 50+interview rounds
  • 8offers
  • 4rejections
  • 500+Claude prep sessions
  1. IGetting in32 min
  2. IIThe system33 min
  3. IIIThe rounds39 min
  4. IVThe loops36 min
  5. VThe offers16 min

Systems deep-dives

Entity ResolutionOct 3, 2026 · 22 min read

Entity resolution at 900M scale

How I built canonicalization pipelines across a 900M-node person graph: precision-first blocking, tiered scoring, and why 74% discard rates are a feature.

Recommendation SystemsOct 2, 2026 · 20 min read

N=1 personalization: Replacing 25 cohorts with user-level ranking

From cohort-based defaults to true user-level personalization at Cars24 UAE: +150% Click Recall@50, +16% buyer conversion, and solving cold-start for 35% of the user base.

Agentic AIOct 1, 2026 · 24 min read

Building a neuro-symbolic trading platform under SEBI compliance

How I architected a 5-layer system where LLMs plan and deterministic policy engines execute, with zero hallucination-induced regulatory breach, by design.

Agentic AIPart 1Nov 2, 2026 · 11 min read

Inside āagman: the system map

The whole of āagman, an AI trading desk for Indian markets, on one page: the constraints that shaped it, the services, the data stores, and the path of one request from a sentence to a broker order.

Agentic AIPart 2Nov 2, 2026 · 7 min read

A strategy language the model can’t escape

The JSON DSL at the center of āagman: why the LLM’s only output is a typed strategy document, what the grammar covers, how the compiler turns it into an execution plan, and where the design stops protecting you.

Agentic AIPart 3Nov 2, 2026 · 7 min read

The agent desk: routing, worker agents and memory

How āagman turns a sentence into a typed strategy: an intent classifier, one orchestrator with a supervisor tool, five stateless worker agents, a staged workflow with a clarifying loop, two layers of memory, and the distilled router and semantic cache that avoid most expensive calls.

InfrastructurePart 4Nov 2, 2026 · 9 min read

A backtester you can put a golden test on

How āagman’s backtesting engine works: a pinned VectorBT core in a sandbox, next-bar fills, intrabar stop rules, golden tests on frozen data, and an honest list of what the first version leaves out.

InfrastructurePart 5Nov 2, 2026 · 8 min read

Market data and a 500-symbol screener

The data platform under āagman: Yahoo Finance and Alpha Vantage ingestion with Prefect, ClickHouse and Postgres storage, a Parquet export for the sandboxed backtester, and a batched, vectorized screener that scans 500+ instruments.

InfrastructurePart 6Nov 2, 2026 · 7 min read

Cheap first: the NSE announcements pipeline

The announcements pipeline behind āagman’s research agent: ingest, extract text, extract fields with rules first and a capped LLM fallback, and classify into 13 categories, with idempotent stages, a dead-letter queue and a windowed backfill.

Agentic AIPart 7Nov 2, 2026 · 8 min read

Four gates before the broker

The pre-trade controls for āagman: a kill switch, a daily loss cap, circuit breakers and a margin check, decided by a policy engine from inputs the model can’t touch, plus the readiness gate, the plan-bound approval and the failure matrix.

InfrastructurePart 8Nov 2, 2026 · 10 min read

Execution from the user’s own machine

The last mile of āagman: a Manifest V3 Chrome extension that drives the user’s own logged-in broker session, how signed execution requests reach it, the order types and brokers it supports, and how fills are reconciled.

InterviewsPart 1Oct 15, 2026 · 12 min read

35 companies, 50+ interviews, 8 offers

A data scientist’s seven-month job search across 35 companies, ending in eight offers and a Google SWE III role in AI/ML. The funnel, the timeline and the system that held it together.

Google interviewPart 2Oct 15, 2026 · 11 min read

From “can’t start” to a plan: baselining for a Google loop

How I turned a self-assessment with zeros in dynamic programming and statistics into a ranked prep plan for a Google ML loop, and what happened when the dates kept moving.

InterviewsPart 3Oct 15, 2026 · 11 min read

The 10 habits that cost me interview signal

Across 50+ interview rounds I tracked ten verbal and structural habits that hid what I knew. Four died, two improved, and four were still there in August. The debrief loop, the drills, and what worked.

InterviewsPart 4Oct 15, 2026 · 9 min read

Running 17 interview processes in one month

In April 2026 I had live interview processes with 17 companies, 24 rounds and three take-homes in flight in the same week. The operating model that kept it from collapsing, and what I would cap next time.

LLM coachingPart 5Oct 15, 2026 · 11 min read

Running my interview prep on Claude

Over five months I ran more than 500 conversations with Claude to prepare for a Google ML loop and the rest of a 35-company search. The documents, rules and session protocols that made it work, and where the AI coach was wrong.

CareerPart 6Oct 15, 2026 · 10 min read

Rebuilding a resume that scored 3.5 out of 10

A hostile review scored my ML engineer resume 3.5 out of 10 on how much a hiring manager would discount. Five versions later it was under 2. The teardown loop, the claims that survive a committee, and defending every line in interviews.

DSAPart 7Oct 15, 2026 · 10 min read

Eighteen days, 102 questions: a DSA sprint

Twelve open data structure and algorithm patterns, 18 days to Google’s onsite coding rounds, and a bank of 102 questions mapped to dates. The sprint design, the daily miss logs, and why process gaps mattered more than algorithms.

InterviewsPart 8Oct 15, 2026 · 9 min read

The rejections, and the round I thought I had failed

Four companies rejected me in a 35-company search, at four different stages. One round I was sure I had failed became an offer. What each rejection taught, and why post-round self-assessment is close to useless.

Google interviewPart 9Oct 15, 2026 · 10 min read

Preparing for the Google ML domain round

How I prepared for Google’s ML and AI domain round at L4: a topic universe built from the recruiter’s scope, from-scratch implementations, debugging scenarios, resume defense and a week of clean-room mocks. It came back Strong Hire.

InterviewsPart 10Oct 15, 2026 · 10 min read

Getting interviews: recruiters, outreach and applications

How 35 companies ended up in conversation with me in 2026: applications with a human note, recruiter replies, cold outreach to hiring-side people, warm reconnects, and a portfolio site built in two hours. What worked in each channel.

Google interviewPart 11Oct 15, 2026 · 10 min read

Preparing for Googleyness and Leadership

How I prepared for Google’s Googleyness and Leadership round: eight stories in a conclusion-first structure, the correction that reversed my “we versus I” rule, metric drills, rapid-fire hypotheticals and adversarial mocks. It came back Strong Hire.

InterviewsPart 12Oct 15, 2026 · 9 min read

Four take-home assignments, one workflow

Four take-homes in about five weeks: a classification system, a multi-agent research system, an API service and a schema mapper, all built with a two-track Claude and Cursor workflow. Two led to offers. The designs, the evaluation, and defending AI-assisted code.

Agentic AIPart 13Oct 15, 2026 · 9 min read

Learning agentic AI for an interview in a week

After clearing Google’s main loop, I got a team-specific round on agentic AI with about a week to prepare, despite never having used the popular agent frameworks in production. How I mapped my own systems onto their vocabulary, rebuilt sessions that did not stick, and what the mocks exposed.

Google interviewPart 14Oct 15, 2026 · 9 min read

The Google loop, round by round

Every round of my Google Software Engineer III loop in AI/ML, from the first recruiter call to the signed offer: format, result, what decided each one, and the coding round I passed with a wrong algorithm. No interview questions.

CareerPart 15Oct 15, 2026 · 8 min read

Choosing between eight offers

Eight offers arrived between April and August 2026, at different times, in different shapes, with different risks. How I read each one, the contract clauses I nearly missed, the rule I used to decide, and how I declined six of them.

CareerPart 16Oct 15, 2026 · 8 min read

Negotiating with Google without a competing offer

By the time Google’s offer call came, every other offer I had was declined or lapsed. How I prepared in an hour, which parts of a Google L4 package actually move, how I framed an ask with no competing offer, and where it landed.