Ahsaas
Bajaj

ML Tech Lead & Applied AI Researcher

Building production AI at Instacart — where my work on personalized fulfillment intelligence has driven $200M+ in influenced GTV and is cited in company shareholder letters. Previously at Samsung R&D and Walmart. Research cited 127+ times. 4 patents.

Ahsaas Bajaj
$200M+ Influenced GTV
127 Research Citations
4 Patents
300M+ Annual Requests

I'm a Machine Learning Tech Lead and applied AI researcher known for designing and shipping large-scale recommendation, retrieval, and personalization systems. At Instacart, I've led the ML architecture for personalized product substitution — a capability publicly credited in shareholder letters for improving customer satisfaction and repeat orders. These systems handle hundreds of millions of item replacements annually at sub-100ms latency.

My career spans Samsung R&D, where I built on-device AI for flagship Galaxy devices, and Walmart, where I built grocery recommendation systems at scale. I hold an MS in Computer Science from UMass Amherst, where I published research under Prof. Andrew McCallum in collaboration with Goldman Sachs.

Member of the Forbes Technology Council, IEEE Senior Member, and International Academy of Digital Arts & Sciences. Invited reviewer for AAAI, KDD, ACL, WWW, and UMAP — 12+ program committees.

Projects & Impact

Instacart
2022 – Present

Intelligent Product Replacement System

Sole ML engineer and de facto technical lead for Instacart's business-critical substitution ranking system. Evolved through four major architectural phases — multi-stage retrieval + deep ranking, explicit negative event modeling, personalized multi-surface ranking, and real-time re-architecture achieving ~11ms p99 latency. LLM-curated denylists and semantic retrieval eliminated worst-case failures. Work cited in Q2 & Q4 2025 and Q4 2024 Instacart Shareholder Letters. Individual Tech Achievement Award, Q4 2024.

$202M+ influenced GTV $25.5M+ contribution profit 300M+ annual requests 78% → 82% conversion
Samsung R&D
2017 – 2019

On-Device Unified Search & Personalized Ranking

Founding member of Samsung's on-device AI team. Designed a FlatBuffers-based serialization architecture for dictionary tries that cut first-query latency 40× (2s → 50ms). Implemented Rocchio query expansion and TF-IDF semantic matching for a 25% recall improvement. Built on-device LTR models (RankSVM, LambdaMART) reused for Bixby card and notification ranking. Shipped on Galaxy S10+ and subsequent flagships — 5M queries/day. Published 4 peer-reviewed papers.

40× latency improvement +25% recall 5M daily queries 4 papers published
UMass / Goldman Sachs
2020 – 2021

NLP Research — Summarization & Relation Extraction

Under Prof. Andrew McCallum, built a GPT-2-based saliency classifier for low-resource long document summarization, outperforming strong baselines by +6 ROUGE points (ACL 2021, 83 citations — cited by Google Research at NeurIPS 2023). Proposed a nearest-neighbors relation prediction method for scientific text, outperforming prior work by up to +3 F1 points (EMNLP 2020). Applied in collaboration with Goldman Sachs for financial document NLP.

ACL 2021 83 citations Cited by Google Research NeurIPS 2023

Career

Mar 2026 – Present
New York City
Machine Learning Tech Lead — Applied AI
Instacart
  • Building next-generation recommender systems at the intersection of generative AI and traditional ML, powering discovery and relevance at scale
  • Developing hyperpersonalized marketing agents that leverage AI to drive customer engagement and conversion
  • Creating AI-powered product experiences including personalized meal planning
Mar 2025 – Mar 2026
New York City
Senior Machine Learning Engineer II (L6)
Instacart — Content AI
  • Drove 5pp year-over-year improvement in perfect order fill rate via dietary, preference, and LLM-derived signals
  • Built AIQA evaluation framework achieving 82% human agreement, compressing annotation cycles from weeks to hours
  • Work highlighted in Instacart Q2 and Q4 2025 Shareholder Letters
Sep 2023 – Mar 2025
San Francisco
Senior Machine Learning Engineer (L5)
Instacart — Content AI
  • ML lead for product substitutions — redesigned ranking architecture, reducing poor replacements ~30% (~$150M in retention)
  • Introduced LLM-augmented features and 10× training data expansion; called out in Q4 2024 Shareholder Letter
  • Designed large-scale experimentation frameworks across 300M+ annual requests
Apr 2022 – Sep 2023
San Francisco
Machine Learning Engineer II (L4)
Instacart — Content AI
  • Built Instacart's replacement recommendation system from scratch — serving real-time predictions across customer, shopper, and ads surfaces
  • Designed end-to-end ML pipeline on AWS SageMaker, MLflow, TensorFlow, and Airflow
  • Co-invented patented ML approach to product substitution ranking (US20240362696A1)
Feb 2021 – Apr 2022
Data Scientist
Walmart Global Tech — Search & Personalization
  • Built large-scale grocery recommendation systems for millions of customers; led repurchase journey and product affinity modeling
  • 1% basket prediction improvement through advanced affinity modeling — granted US Patent (US12406282B2, cited by Pinterest)
Jul 2017 – Aug 2019
Bangalore, India
Software Engineer → Senior Software Engineer
Samsung R&D Institute — On-Device AI
  • Founding member of on-device AI team; built and shipped intelligent search engine across Samsung flagship devices (5M+ daily queries)
  • 40× first-query latency improvement and 25% recall boost via novel retrieval architecture
  • Published 4 peer-reviewed papers at ACM CODS-COMAD, NLDB, and CICLing

Publications & Patents

Articles & Coverage

Talks & Engagements

Free live webinar — how AI transforms raw data into intelligent decisions powering recommendations, search, fraud detection, and dynamic pricing
March 2026 · Virtual
Production-grade ML systems and real-world recommendation challenges. Watch →
January 2026
Data Science Salon — DSS Break
Applied ML, system design, and evaluation in industry. Watch →
February 2026
Louisville AI Week
Featured Speaker & Panelist — large-scale recommendation systems and applied ML in e-commerce
February 2026
New York AI Engineers Tech Talk
ML systems for e-commerce and personalization
May 2026
Panel: From single models to modular systems — Architecting reliable next generation AI
June 2026 · New York
Data Science Salon — E-commerce & Retail
Applied ML: quality, evaluation, and business impact at scale
June 2026 · Seattle
The Data Science Conference (TDSC)
Production ML systems and real-world applications
May 2026 · Chicago
ACL-IJCNLP 2021
Long Document Summarization in a Low Resource Setting. Watch →
August 2021 · Virtual
EMNLP 2020
Shallow Semantic Parsing in Scientific Procedural Text. Watch →
November 2020 · Virtual

Awards, Memberships & Service

Invitation-only membership (10–11% acceptance rate) for senior technology leaders
IEEE Senior Member
Recognizing sustained significant performance in IEEE-designated fields
Associate member · Webby Awards judge for excellence on the internet
Instacart Individual Tech Achievement Award
Recognized for exceptional technical contributions and high-impact ML initiatives, Q4 2024
Applied AI Technical Advisor — AI Circle
Technical advisor on Applied AI within AI Circle, an invite-only community of AI leaders
Technical Advisor — Bhasha Tech
ML advisory for AI-powered English learning app with 50K+ users in 130+ countries
Academic Program Committees
Invited reviewer for 12+ conferences: AAAI, KDD, ACL, WWW, UMAP, NLDB, and more (2022–present)
Expert committee for DSCNext Conference on data science and AI
Samsung Citizen Award
Outstanding performance and contributions beyond functional scope · Software Competency: Professional
Hackathon & Startup Demo Jury
Invited judge evaluating student and early-stage innovation across five programs in 2026: DevFest Columbia · YHacks · Live Ivy Global Hackathon · Webby Awards (AI category) · UMass Mini Startup Series

Open to collaborations,
advisory, and speaking.

The best way to reach me is by email.