Sachin Aggarwal — CTO

I build production-grade AI systems that actually work in the real world. Over the past few years, I’ve been focused on Applied AI—designing and scaling LLM-powered systems for complex, unstructured workflows like document processing. My work sits at the intersection of backend systems, AI, UI and platform engineering. Currently leading development of an Intelligent Document Processing (IDP) platform at Avalara, processing ~150K documents/week through end-to-end pipelines involving OCR, classification, extraction, and summarization. Key areas I work on: • LLM & Agentic Systems: multi-stage workflows with confidence scoring, citations, human-in-the-loop review, and evaluation loops • AI Platform Engineering: building reliable pipelines using Temporal, queues, and distributed processing • Applied AI Optimization: improving accuracy (60% → 92%) via automated prompt tuning, evaluation systems (GEPA, TextGrad), and feedback loops • Scalability & Reliability: handling large documents with parallel processing, retries, observability (Prometheus, Grafana), and cost optimization • I also bring strong product and user experience intuition—having built frontend systems (React/TypeScript) and actively shaping user journeys, review workflows, and human-in-the-loop interfaces for AI systems. Tech stack: Python, FastAPI, LLMs, RAG, Temporal, Redis, AWS, Kubernetes, React.js, Vue.js I’m particularly interested in: • Applied AI / GenAI systems • Agentic workflows & orchestration • AI infrastructure & platform engineering

Stackforce AI infers this person is a SaaS expert specializing in AI systems and platform engineering.

Location: Gurugram, Haryana, India

Experience: 9 yrs 8 mos

Skills

Large Language Models (llm)
Systems Design
React.js
Node.js

Career Highlights

Led development of scalable AI document processing platform.
Improved extraction accuracy from 60% to 92%.
Strong expertise in LLM and AI platform engineering.

Work Experience

Avalara

Technical Lead (1 yr 10 mos)

Senior Software Engineer (2 yrs 5 mos)

Software Engineer 2 (R&D) (2 yrs 1 mo)

QuickReply.ai

Principle Software Engineer (11 mos)

Indix

Software Developer (5 mos)

IntelliTicks

Intern (4 mos)

Google

Google Summer of Code Intern (Anita Borg Community, Systers) (3 mos)

Anita Borg Institute for Women in Technology

Contributor (5 mos)

BuildmLearn

Contributor (7 mos)

Microsoft India

Microsoft Student Partner (1 yr 7 mos)

Education

Engineer’s Degree at Maharaja Agrasen Institute Of Technology, Delhi

at Mira Model School,Janak Puri,New Delhi

Sachin Aggarwal

CTO

Gurugram, Haryana, India9 yrs 8 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Led development of scalable AI document processing platform.
Improved extraction accuracy from 60% to 92%.
Strong expertise in LLM and AI platform engineering.

Stackforce AI infers this person is a SaaS expert specializing in AI systems and platform engineering.

Contact

Skills

Core Skills

Large Language Models (llm)Systems DesignReact.jsNode.js

Other Skills

OCRclassificationextractionsummarizationTemporalPrometheusGrafanaAmazon Web Services (AWS)ElasticsearchMongoDBVue.jsAG-gridAkkaAutomationScala

About

Experience

9 yrs 8 mos

Total Experience

1 yr 3 mos

Average Tenure

1 yr 10 mos

Current Experience

Avalara

3 roles

Technical Lead

Promoted

Jul 2024 – Present · 1 yr 10 mos · Pune District · Remote

Leading the development of a scalable Intelligent Document Processing (IDP) platform, supporting end-to-end workflows across OCR, extraction, classification, summarization, etc.
Architected Temporal-based distributed workflows with chunking and parallel processing for large documents, enabling reliable OCR + LLM pipelines at scale (~150K docs/week).
Built a production-grade extraction agentic system for documents - confidence scoring, HITL review, citations, redactions, and evaluation pipelines for reliable and explainable LLM workflows.
Improved extraction accuracy from ~60% -> ~92% via closed-loop system: auto prompt tuning driven by evaluation pipelines, ground truth, and user feedback (GEPA, TextGrad).
Resolved memory retention and spike issues arising from large document/image processing, reducing memory usage by around 40% and stabilizing production workloads.
Implemented observability (Prometheus, Grafana, tracing) to improve system reliability, debuggability, and platform stability.

Large Language Models (LLM)Systems Design

Senior Software Engineer

Promoted

Mar 2021 – Aug 2023 · 2 yrs 5 mos

Lead the development of a spreadsheet based classification tool by performing POC of different solutions and using feature rich AG-grid that reduced the manual classification time by 40% and saved x$ per month in cost.
Integrated classification use cases from different teams under one self-serve UI based on user roles that reduced cross team bottlenecks and got released to customers contributing x$ towards the revenue.
Automated the manual tests with functional test suite and added periodic validations for the public facing website.
Redesigned the UI of the HS Code Annotation app which streamlined the annotation process and reduced time
taken by 30%.

Vue.js

Software Engineer 2 (R&D)

Feb 2019 – Mar 2021 · 2 yrs 1 mo

Automated the detection of tax changes in all US states which are published as documents (around 2k documents in different strcuture and file formats) reducing the time taken by the tax researchers by 60%.
Devised a feedback workflow that detected technical gaps in our automation engine and provided feedback for the ML models to plan further improvements.
Oversaw the monthly run of product data spark pipelines which generates around 2.4 billion unique products.
As part of Indix acquisition by Avalara, I migrated various services and our product data pipelines to Avalara.
Currently taking upon new domains that can be taken for automation and their implementation (scala language).

Akka

Quickreply.ai

Principle Software Engineer

Aug 2023 – Jul 2024 · 11 mos · Gurugram · On-site

Led the development of the design system in React after identifying the requirements with the UX team.
Developed conversation service handling 20k socket connections at peak, featuring dynamic filters & messaging.
Revamped the conversations UI in the platform as per the UX Figma designs and utilizing the design system.
Led the architectural decisions for building the Customer Data Platform, Merging attributes of the same customers,
Syncing customer data from CRMs to internal DB to resolve dependencies and providing segmentation on this
customer data. Used Node.js, MongoDB, etc.
Led the development of Flow builder that enables the users to create customer journeys by connecting nodes: AB
split, Conditional, Payment, Whatsapp message, Dynamic Code and Wait node. Used Node.js and React.js.
Led the infrastructure setup: Syncing MongoDB and Elasticsearch data, CICD, Alerts, and Monitoring, etc

Amazon Web Services (AWS)Node.jsElasticsearchReact.jsSystems DesignMongoDB

Indix

Software Developer

Aug 2018 – Jan 2019 · 5 mos · Chennai Area, India

Worked on our data service platform, a very general cluster manager which lets you run workloads on the cloud with currently supporting spark jobs which can be run on the EMR cluster (AWS). The platform is responsible for monitoring the data job and its lifecycle which includes both cluster and job lifecycle. Worked on all aspects of the platform and owning the project currently.
Technologies : Scala, Akka Actors and HTTP for backend, Postgres for persistence, Gocd for CI/CD and Kubernetes for deployment.

Akka

Intelliticks

Intern

Mar 2018 – Jul 2018 · 4 mos · Gurgaon, India

Intelliticks is a early-age startup that offered me a lot of challenges, some of which include :
Created log monitoring service for all projects using AWS Cloudwatch, AWS Lambda, etc.
Applied techniques like pagination in existing API endpoints to reduce response time.
Created Event emitter service for messenger engine to emit events at desired times.
Created database & API endpoints for email-reporting service and worked with Mongo Aggregations, indexing.
Fixed major production bugs in Angular frontend of the product.
Created python and shell scripts to automate tasks.
Technologies worked on : AWS, Node.js, Angular, Mongodb, Meteor.js, Linux, Python, Shell scripting, etc.

Google

Google Summer of Code Intern (Anita Borg Community, Systers)

May 2017 – Aug 2017 · 3 mos · Remote · Remote

I worked on Powerup Android project which is aimed at gamifying the learning process for teenagers. It is a choose-your-own-adventure mobile game that teaches social emotional learning, conflict resolution, and health skills in a fun, interactive way. I worked on tasks including :
 Developed various in-play interactive games :
Vocabulary Game which included challenges like handling collisions, multithreading, etc.
Minesweeper game which can be easily scaled to more number of levels.
Swim to Sink Game which makes use of time spent to create different effects during play time.
 Worked on dialogues delivery mechanism using graph based node structure parsed from CSV file.
 Redesigned all layouts of the game for new designs; Ensured support for all Android screen sizes & API levels.
 Added unit tests using Robolectric Framework, continuous integration using Travis CI, and complete documentation for the work and continuous integration with iOS and design teams.
Technologies worked on : Java, Android SDK, Git, Testing, etc.

Anita borg institute for women in technology

Contributor

Oct 2016 – Mar 2017 · 5 mos · Systers

I am working as a contributor to Systers Organisation, Anita Borg Institute. I have contributed in projects like PCSA- Android (2nd biggest contributor), PowerUp Android, Malaria- Android.

Buildmlearn

Contributor

Sep 2016 – Apr 2017 · 7 mos

I am currently the 3rd biggest contributor in BuildmLearn Toolkit project. BuildmLearn is a Open Source organisation modifying the education system in India by providing mobile applications. BuildmLearn Toolkit-Android is only one application available till now which can generate Android Application from a Android application. It lets you generate educational applications for you without having any technical knowledge.

Microsoft india

Microsoft Student Partner

Aug 2015 – Mar 2017 · 1 yr 7 mos · India

As a Microsoft Student Partner, I got the opportunity to interact with Mr. Satya Nadella, CEO Microsoft.
My job as Microsoft Student Partner include working alongside Microsoft professionals assisting them in testing Microsoft products and conducting regular events like presentations to promote Microsoft Technologies.