am·

Abhijit
Krishna Menon

Senior Data Engineer
· Amazon

I take operational problems through data, software, and AI into production.

View / print resume ↗

Data foundations. Applied AI.
Ownership across the stack.

01 / SELECTED WORK

From the first question
to production.

The work I’m drawn to crosses boundaries: a data problem becomes a platform, an analysis becomes a product change, and an AI tool becomes part of someone’s daily workflow.

PLATFORM ENGINEERINGAMAZON / INTERNAL

An analytics platform
that teams can extend.

I worked on the platform and agent harness, including custom SQL-tool onboarding. More than 50 contributors built out the domain context and SQL tools that make it useful across business teams.

CONTRIBUTEDomain context
& SQL tools
PLATFORM & HARNESSSelf-service analyticsMy work: platform setup & engineering
USEBusiness teams
& stakeholders
Custom SQL toolsMCP integrationsCode interpretersEvaluations
Contributor ecosystem and platform capabilities, simplified.
50+context contributors
1,000+stakeholders · 61 teams
48h → 5mtime to insight · 80% of queries
Explore the workClose details
My contribution
Platform setup and engineering of an extensible analytics harness, with custom SQL-based tool onboarding. Contributors supplied domain context and SQL tools.
What it supports
MCP integrations, code interpreters, evaluations, intent and sub-topic routing, retrieval over a knowledge base, and safe, access-controlled answers. The React portal and Python backend support charts, reports, and self-service analytics.
Making it usable
Self-service onboarding of business domains, sources, and knowledge articles, alongside authoring, testing, and CI tooling for skills and topics. Systematic evaluations replaced manual log inspection for quality measurement.
END-TO-END OWNERSHIPAMAZON / OPERATIONS

From operational visibility
to a production control.

I joined a dispute-reduction workstream with no analytics and carried it from metric definition to self-service reporting. When product changes needed engineering capacity, I shipped the customer-facing UI and entry validation too.

  1. 01DefineMetrics & data models
  2. 02UnderstandPipelines & analysis
  3. 03EnableSelf-service reporting
  4. 04PreventUI & entry validation
One workstream, carried across data, backend, and frontend.
Explore the workClose details
Starting point
The program had no analytics around this workstream. I defined metrics, built Redshift models and pipelines, and created reporting that helped operations and BI partners see where excess dispute volume concentrated and what drove it.
Following through
When partner teams lacked capacity for needed product changes, I worked in the customer-facing portal and shipped UI updates and an automated point-of-entry validation gate.
What changed
The work progressed from analysis and recommendations to self-service visibility and a production control. My ownership crossed the data, backend, and frontend boundaries needed to deliver it.
APPLIED AIINTERNAL & PARTNER-FACING

AI in the work
people already do.

Different tools serve different moments: exploring a database, reviewing a query, investigating an incident, or supporting a delivery business. My work spans internal engineering tools and contributions to Amazon DSP Companion.

ENGINEERS
EXPLORERedshift MCP
REVIEWSQL review
INVESTIGATEOn-call agent
DELIVERY PARTNERS
Amazon DSP CompanionAI assistance for delivery-business owners
Engineering stages and a separate partner-facing product; arrows do not imply system integrations.
Explore the workClose details
Explore
Built a Redshift MCP server for schema discovery, query execution, and performance diagnostics. Its secure proxy and identity layer support per-agent identity, audit provenance, and permission guardrails.
Review
Built an agent that executes pull-request SQL against Redshift, parses EXPLAIN plans, and surfaces syntax errors and optimization recommendations before merge.
Investigate
Built an autonomous on-call agent for ticket triage, parallel investigations, root-cause analysis, and automatically posted findings.
External partners
Contributed to Amazon DSP Companion, an AI assistant for Delivery Service Partners. Public launch announcement ↗
Further work
A voice-enabled coaching and learning agent turns performance data into spoken briefings. Reusable permission and ticketing frameworks support multiple applications.

02 / PUBLIC EXPERIMENTS

Things you can try
or take apart.

MENON AGENT LAB

Should this be an agent?

An interactive engineering experiment about choosing between fixed workflows and agents.

Try the experiment ↗
01

LLM-ChessCoach ↗

Chess-game analysis with language-model coaching and separate Stockfish evaluations.

Python / Stockfish / FastAPI
02

AgentHive ↗

A marketplace experiment for specialized AI assistants, with a shared interface and usage tracking.

React / TypeScript / FastAPI
03

ElevateCV ↗

Resume parsing, structured profiles, and job-description-based resume generation.

React / Flask / SQLAlchemy

03 / CAREER & BACKGROUND

The experience
behind the work.

2022 — PRESENT

Amazon

  1. Senior Data EngineerMar 2026 — Present
  2. Data Engineer IIJun 2023 — Mar 2026
  3. Data Engineer IMar 2022 — May 2023
Data infrastructure & earlier workClose details
  • Built multi-tenant file ingestion across SFTP, web UI, and S3, with Spark validation and Parquet processing for 100+ feeds across 20 vendors.
  • Re-engineered delivery-partner scorecards using configurable pipelines, versioning, and Data Vault modeling across 18 metrics. Cut processing runtime from six hours to one.
  • Engineered ingestion, analytics, and payment workflows for Alexa Thank My Driver, supporting $2 million in payments.
2021 — 2022

Chewy

Marketing Data Engineer II · Feb 2021 — Mar 2022

Marketing data pipelines and MLOps infrastructure across AWS accounts.

More about the workClose details

Led an MLOps platform using SageMaker Studio, custom Docker containers, and Feature Store. Built real-time bid adjustments using competitor pricing, increasing customer acquisitions by 55%, and Prophet conversion forecasts that reduced cost per acquisition by 10%.

Education & technical backgroundClose details
Education
MSc, Data Analytics Engineering — Northeastern University, Aug 2020.
BTech, Mechatronics Engineering — SRM Institute of Science and Technology, Jul 2018.
Software
Python, TypeScript, React, SQL, Scala, FastAPI, Docker, AWS CDK, CI/CD.
AI systems
Amazon Bedrock, Strands Agents SDK, LangGraph, MCP, RAG, tool orchestration, code execution, evaluations, identity and access controls.
Data & cloud
Redshift, Spark, Glue, S3, Lambda, DynamoDB, SNS, SQS, EventBridge, Step Functions, IAM, CloudWatch, SageMaker.

LEARNING & CONVERSATION

Building, sharing,
and working things through.

I mentor data engineers on resumes, interview preparation, and career decisions. I also write about ideas I’m learning and exploring.

Find a mentoring session ↗Introduction to Causal Inference ↗