# Keshav Singhal

Keshav Singhal is a remote worker on Himalayas, AI Medical Simulation Engine at AI Medical Simulation Engine, based in India.

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

```text
AI-focused computer science student building evaluated LLM and real-time anomaly systems.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | India |
| Authorized to work in | India |
| Job categories | AI Engineer, NLP Engineer, Machine Learning Engineer, Real Time Systems Engineer, AI Research Engineer, Artificial Intelligence Engineer, AI ML Engineer, Artificial Intelligence Engineering, Python AI Engineer |
| Skills | Lang Chain, RAG, LLM, Large Language Models, LLM Fine tuning, Prompt Engineering, Embeddings, Semantic Search, Reranking, Model Evaluation, PyTorch, scikit learn, Supervised Learning, Unsupervised Learning, Anomaly Detection, Feature Engineering, Isolation Forest, Faiss, Vector Databases, BM25, MySQL, fastAPI, REST APIs, Data Pipelines, Microservices, Session Management, Python, C, SQL, Git, Docker, Linux, GitHub, Kafka, iOS |

## What I'm looking for

```text
I’m looking for a role where I can build and evaluate end-to-end AI systems—LLM/RAG pipelines, real-time anomaly detection, and practical APIs—while iterating from idea to measurable impact and working with a team that values solid evaluation.
```

## About

```text
I’m a CS undergrad with a strong interest in artificial intelligence and the systems built around it. I’ve worked across AI, from language models and retrieval systems to real-time data and anomaly detection, and I’m comfortable taking projects from idea to a working, evaluated system.

Recent work includes a Legal AI system using hybrid retrieval and a fine-tuned LLaMA model, with an evaluation framework pairing automated metrics and expert (lawyer) assessments (paper targeting JURIX 2026). I’ve also built a real-time threat detection pipeline with Apache Kafka and FastAPI using Isolation Forest/Autoencoders, plus LLM-based human-readable report generation, and I’m continuing to explore LLM-powered conversational simulation with controlled dialogue behavior and robust evaluation.
```

## Experience

### AI Medical Simulation Engine (current)

AI Medical Simulation Engine. Mar 2026 - Present

```text
Developed an LLM-powered clinical simulation engine supporting realistic multi-turn patient–doctor conversations. Built a FastAPI backend with session management and a hybrid evaluation approach combining rule-based scoring with LLM-generated qualitative feedback.
```

Skills: Multi-Turn-Conversational-AI, fastAPI, Session-Management, Prompt-Engineering

### Real-Time Threat Detection (current)

AI-Powered Threat Detection & Analysis System

```text
Created a high-throughput real-time network log pipeline using Kafka and FastAPI, generating interpretable anomaly reports via LLM integration. Implemented Isolation Forest and Autoencoder models for anomaly detection on CICIDS2017 and exposed monitoring and historical analysis via REST APIs.
```

Skills: Kafka, fastAPI, REST-APIs, Anomaly-Detection, Isolation-Forest, LLM-Integrations, Network-Log-Processing, Report-Modeling

### JurisPro Legal AI System (current)

JurisPro

```text
Built a hybrid RAG system for an Indian legal corpus combining BM25 sparse retrieval and FAISS dense retrieval. Fine-tuned LLaMA 3.1-8B on legal data and reduced training loss from 1.87 to 0.82 over 1500 steps, with an ablation-based evaluation framework aimed at a JURIX 2026 paper.
```

Skills: RAG, LLM-Fine-tuning, BM25, Faiss, Reranking, Model-Evaluation, Prompt-Engineering

### Kafka Real-Time Streaming System (current)

Kafka-Based Real-Time Streaming System

```text
Built a scalable Kafka ingestion pipeline using a producer-consumer architecture for continuous, high-throughput processing. Designed streaming workflows to support ongoing data ingestion and processing at scale.
```

Skills: Kafka, Producer-Consumer-Architecture, Data-Ingestion, High-Throughput-Systems, Scalability

## Education

### PES University

Bachelor of Technology, Computer Science and Engineering. 2023 - 2027

```text
Pursuing a B.Tech in Computer Science and Engineering at PES University, Bengaluru (expected 2027). Focused on building a strong foundation in AI and related systems.
```

### Hope Hall Foundation School

CBSE Class XII, Secondary Education. Grade: 87.6%

```text
Completed CBSE Class XII at Hope Hall Foundation School in New Delhi in 2023 with 87.6%.
```

### Delhi Public School, Indirapuram

CBSE Class X, Secondary Education. Grade: 96%

```text
Completed CBSE Class X at Delhi Public School, Indirapuram in 2021 with 96%.
```

## Tech stack

- GitHub
- MySQL
- Gmail
- PyTorch
- scikit-learn
- Kafka
- FastAPI
- Linux
- iOS
- SQL
- LangChain
- Faiss
- Keep
- X++

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

## People also viewed

- [Gunavathi R Bhat](https://himalayas.app/@gunavathirbhat): AI/ML Engineer, AIML TechnoSystems
- [Nikunj Aindrawar](https://himalayas.app/@nikunjaindrawar): Research & Development Member, Encrypt: The Tech Society of College of Vocational Studies
- [Pranjal Raghava](https://himalayas.app/@pranjalraghava): Data Scientist, ValueMatrix AI
- [Suraj Patel](https://himalayas.app/@surajpatel4): Machine Learning Engineer, Self Employed
- [Harshit Vashisth](https://himalayas.app/@harshitvashisth): Data Science Intern, Medtek.ai
- [Aryan Sivanandan](https://himalayas.app/@aryansivanandan): AI Engineer Intern, Applied AI Consulting (AAIC)
- [adhil muhammed](https://himalayas.app/@adhilmuhammed1): Generative AI Engineer, Self Employed
- [ANUSHKA AGARWAL](https://himalayas.app/@anushkaagarwal): AI/ML Summer Intern, Zenithive
- [Tushar Saxena](https://himalayas.app/@tusharsaxena1): AI Intern, Lawcentral
- [Hamza Khan](https://himalayas.app/@hamzakhan47): AI Engineer, MPIRIQ
