# Ishan Aggarwal

Ishan Aggarwal is a remote worker on Himalayas, Software Engineer at Data Alchemy AI, based in United States.

Source: https://himalayas.app/@ishanaggarwal

```text
Software Development Engineer building fault-tolerant cloud systems and LLM-powered APIs.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | United States |
| Authorized to work in | United States |
| Job categories | Software Development Engineer, AI Machine Learning Engineering, Cloud Computing Engineering, Software Engineer, Software Developer, DevOps Engineer |
| Skills | REST APIs, NodeJS, Python, Java, C#, Go, TypeScript, SQL, React, Angular, fastAPI, Node.Js Development, GraphQL, AWS ECS, AWS Lambda, Azure, Kubernetes, Docker, Helm, Terraform, CI CD, High Availability, PostgreSQL, MySQL, MongoDB, DynamoDB, Redis, Faiss, Prometheus, Grafana, ELK Stack, RAG, Sentence Transformers, PyTorch, MLOps, Model Quantization, Data Structures, Algorithms, System Design, Distributed Systems, Azure Kubernetes Service, Core Data, Firebase, GitHub, GitHub Actions, HTML5, JavaScript, Stack AI, SwiftUI, WebRTC, iOS, Minikube, Lang Chain, LLM |
| Portfolio | https://github.com/ishanaggarwal/query-agent-sample |

## What I'm looking for

```text
I’m looking for a role where I can design fault-tolerant distributed services and high-throughput APIs, scale LLM inference with strong observability, and collaborate cross-functionally to ship measurable latency, availability, and cost improvements.
```

## About

```text
I’m a Software Development Engineer with 2+ years building cloud-native distributed systems and high-throughput APIs across fintech and AI platforms. I focus on system reliability and performance—delivering fault-tolerant microservices processing $2B+ in daily transactions at 99.95% availability.

In my current role at Data Alchemy AI, I architect an AI Interview Coach and Data Catalog using GPT, Claude, LangChain, WebRTC, and Azure OpenAI. I’ve delivered sub-200ms real-time voice coaching with multi-turn conversational memory, and I deployed multi-tenant LLM agents on Azure Kubernetes Service with session-aware context management—reducing context retrieval overhead by 3x across 500+ concurrent users.

Previously at Otomashen Inc., I built GPT-4 and BERT recommendation engines with RAG across 100,000+ educational resources, improving course completion from 12% to 34%. I also engineered LLM inference infrastructure on AWS EKS using model quantization and GPU-accelerated serving, processing 8,000+ requests/day at 40% lower compute cost while maintaining 99.9% availability.

Earlier, at Bank of America, I redesigned a legacy monolith into 15+ fault-tolerant Python microservices with Docker, ECS, and Terraform on AWS—reaching 99.95% uptime and eliminating $1.2M in annual infrastructure costs. I bring a strong foundation in data structures, algorithms, and system design, and I enjoy turning experimentation into standards through A/B testing, observability, and cross-team iteration.
```

## Experience

### Software Engineer (current)

Data Alchemy AI. Oct 2025 - Present

```text
Architected an AI Interview Coach and Data Catalog using GPT/Claude and LangChain, delivering sub-200ms real-time voice coaching with multi-turn conversational memory and fault-tolerant sessions. Deployed multi-tenant LLM agents on Azure AKS, reducing context retrieval overhead 3x across 500+ concurrent users, and cut LLM iteration cycles from 3 days to under 6 hours (12x).
```

Skills: Azure-OpenAI, Claude, Lang-Chain, WebRTC, AKS-(Kubernetes), AI-Agents, Conversational-Memory

### Software Engineer (Co-op)

Otomashen Inc.. Jan 2025 - Jun 2025

```text
Built a GPT-4/BERT recommendation engine with a RAG pipeline over 100,000+ educational resources, increasing course completion rates from 12% to 34% (183% lift). Architected LLM inference infrastructure on AWS EKS with model quantization for 8,000+ requests/day at 40% lower compute cost while maintaining 99.9% availability.
```

Skills: GPT-4, BERT, Model-Quantization, GPU-Accelerated-Serving, A-B-Testing, High-Availability, RAG

### Research Assistant

Northeastern Civic AI Lab. Jan 2024 - Apr 2025

```text
Fine-tuned BERT on political speech data using RLHF, achieving 89% accuracy and 25% bias reduction. Mentored 40+ graduate students and led hands-on AI/ML workshops to support continuous learning.
```

Skills: NLP, Transformers, Workshop-Facilitation, Experimental-Design

### Software Engineer

[Bank of America](https://himalayas.app/companies/bank-of-america). Jun 2022 - Jul 2023

```text
Redesigned a legacy investment platform into 15+ fault-tolerant Python microservices deployed via Docker, ECS, and Terraform on AWS, achieving 99.95% uptime and eliminating $1.2M in annual infrastructure costs. Built a FastAPI gateway with load balancing, Redis caching, and JWT auth to sustain 10,000+ req/s and sub-50ms p99 latency under peak load, and orchestrated Kubernetes migrations using HPA
```

Skills: Microservices, fastAPI, Docker, AWS-ECS, Terraform, Redis, JWT, Deployment, Kubernetes, SPOT-Instances

### Software Engineering Intern

AWC Software Pvt. Ltd.. Jan 2021 - Jun 2021

```text
Revamped 10+ web apps using React and TypeScript with lazy loading and code splitting, improving page load performance by 45%. Automated CI/CD with GitHub Actions, Docker, and AWS S3/CloudFront, reducing deployment time from 4 hours to under 30 minutes.
```

Skills: React, TypeScript, Lazy-Loading, GitHub-Actions, Docker, CI-CD, S3, Amazon-Cloudfront

## Education

### Northeastern University

Master of Science, Computer Science. 2023 - 2025

```text
Pursued a Master of Science in Computer Science, covering coursework in program design, web development, data structures and algorithms, cloud, databases, NLP, and AI foundations.
```

### Vellore Institute of Technology

Bachelor of Technology, Information Technology. 2018 - 2022

Activities and societies: Winner/finalist at 4+ major technical hackathons; delivered full-stack AI prototypes within 48-hour constraints.

```text
Earned a Bachelor of Technology in Information Technology, with experience building full-stack AI prototypes during multiple technical hackathons.
```

## Tech stack

- Microsoft Azure
- GitHub
- Kubernetes
- minikube
- Azure Kubernetes Service
- GitHub Actions
- MySQL
- PostgreSQL
- MongoDB
- Gmail
- Node.js
- Redis
- Terraform
- JavaScript
- HTML5
- Java
- PyTorch
- FastAPI
- SwiftUI
- Grafana
- Prometheus
- iOS
- GraphQL
- Firebase
- WebRTC
- SQL
- Core Data
- LangChain
- Faiss
- Stack AI
- Sentence Transformers

To contact Ishan, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Shrey Bhadiyadara](https://himalayas.app/@shreybhadiyadara): Software Development Engineer, Scale AI
- [Michael Lubich](https://himalayas.app/@michaellubich): Senior Software Engineer, Braintrust Data
- [Mickey Liu](https://himalayas.app/@mickeyliu): Senior Software Engineer, Notion
- [genna User](https://himalayas.app/@maarouf): Sr. AI/ML Software Engineer, Remitly
- [Syed Raza](https://himalayas.app/@syedraza4): Senior Full Stack & AI Engineer, Raytheon Technologies
- [Jerry Yang](https://himalayas.app/@jerryyang1): Backend & AI Developer, Microsoft
- [Miguel Saldana](https://himalayas.app/@miguelsaldana1): Senior Software Engineer (AI & Agentic Systems), SoftServe
- [Qiang Zhang](https://himalayas.app/@qiangzhang): Member of Technical Staff – Foundation Models & AI Systems, OpenAI
- [Dustin Briscoe](https://himalayas.app/@dustinbriscoe): Lead AI Engineer, Cogentic Labs Inc.
- [Bryan Ho](https://himalayas.app/@bryanho): Staff Software Engineer, Robinhood
