# Abhinav User

Abhinav User is a remote worker on Himalayas, Data Scientist Intern at Simpplr, based in India.

Source: https://himalayas.app/@abhinavuser25

```text
Data Scientist Intern at Simpplr who cut RAG answer latency by 60% and cost per token by 40%.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 1196k+ INR |
| Job categories | Data Scientist, Machine Learning Engineer, AI Engineer |
| Skills | Data Science, Large Language Models, Search Model Optimization, RAG, Causal Inference, A B Testing, Uplift Modeling, Forecasting, MLOps, LLM Evaluation, Python, SQL, Pandas, NumPy, DuckDB |

## About

```text
At Simpplr, I evaluate and optimize production LLM and search models for accuracy, latency, and cost. I replaced a paid LLM API with self-hosted search intent classifiers, improving accuracy from 95.7% to 99.1% and lowering p50 latency by 3–6×.

I also optimized the RAG answer engine, reducing latency by 60% and cost per token by 40% while supporting 8× more concurrent users. Prompt restructuring raised capacity 26×, and I cut a 33-hour job to 12.7 hours while reducing GPU cost by 17–21%.

In my projects, I built an experimentation and causal inference toolkit tested on real ASOS experiments and Criteo users, and a demand forecasting service for Walmart M5 data. The forecasting system used LightGBM, a dbt and DuckDB feature pipeline, and an MLflow model gate; its winning model reduced item-level WAPE by 18.5% versus seasonal naive.
```

## Experience

### Data Scientist Intern (current)

[Simpplr](https://himalayas.app/companies/simpplr). May 2026 - Present

```text
Evaluated and optimized production LLM and search models on GPUs for accuracy, latency, and cost. Replaced a paid LLM API with self-hosted search intent classifiers, improving accuracy from 95.7% to 99.1% and reducing p50 latency by 3-6x.
```

Skills: LLM, Search, GPU, RAG, IFEval, CrossNER, Benchmarking, Quality-Gates, Cost-Optimization, Latency-Optimization

## Education

### Indian Institute of Technology, Kharagpur

B.Tech (Hons.) + M.Tech, Mechanical Engineering. 2021 - 2026. Grade: 8.02/10

```text
Pursued a dual degree program in Mechanical Engineering with a specialization in Manufacturing Sciences and Engineering, achieving a GPA of 8.02/10.
```

### KMD Public Sr. Sc. School, Jaipur

Higher Secondary (12th Board), General. Grade: 90.60%

```text
Completed Higher Secondary (12th Board) with a percentage of 90.60%.
```

## Tech stack

- GitHub Actions
- NumPy
- Pandas
- dbt
- Python
- PyTorch
- MLflow
- scikit-learn
- FastAPI
- Docker
- SQL
- LightGBM
- DuckDB
- vLLM

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

## People also viewed

- [Ravi kumar Gubbala](https://himalayas.app/@ravikumargubbala): AI Platform Engineer, LLM Sandbox
- [DIVYA SONI](https://himalayas.app/@divyasoni1): Data Analyst in Research and Development, Force Motors
- [Jagruti Yuvraj Dhangar\_DataSci](https://himalayas.app/@jagrutiyuvrajdhangar): Machine Learning Intern, Internshala
- [aksh modi](https://himalayas.app/@akshmodi): Cohort Participant & Contributor, MediaWiki Cohort 2 (Road to Wiki Tech)
- [Lokesh Gupta](https://himalayas.app/@lokeshgupta): Business Analyst Intern, Cashflo
- [Mohit Awasthi](https://himalayas.app/@mohitawasthi): Data Scientist II, MiQ Digital Private Limited
- [Aswin K J User](https://himalayas.app/@aswinkjuser): ML Intern, FlyRank
- [Katyayani Upadhyay](https://himalayas.app/@katyayaniupadhyay): AI Engineer Intern, GobbleCube
- [Nihal Mishra](https://himalayas.app/@nihalmishra1): Machine Learning Intern, Flyrank AI
- [Prathamesh Work](https://himalayas.app/@prathameshwork): Data Science Intern, NexGen Analytix
