# Ramsha Anwar

Ramsha Anwar is a remote worker on Himalayas, AI Pharmacovigilance Drug Safety Monitor at AI Pharmacovigilance Drug Safety Monitor, based in Pakistan.

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

```text
Final-year Computer Science student building agentic AI and LLM systems.
```

| Detail | Value |
| --- | --- |
| Availability | Open to opportunities |
| Location | Pakistan |
| Authorized to work in | Pakistan |
| Job categories | Agentic AI Systems, LLM Engineering, AI Machine Learning Engineering, AI Systems Engineering, Fullstack Development, Backend Development, AI Agentic Systems, Agentic AI, Agentic AI Platforms, Agentic AI Solutions, Agentic AI Development |
| Skills | Lang Chain, Python, TypeScript, SQL, fastAPI, NestJS, React 19, Tailwind, Anthropic: Claude, GROQ, LLaMA 2, OpenAI, LoRAs, QLoRA, PEFT, RAG Data Pipelines, Sentence Transformers, scikit learn, NumPy, Weights Biases, LangGraph, Multi Agent Checkpoints, Human In The Loop, Agentic AI, AutoGen, Model Context Protocol (MCP), ReAct Pattern, Self Reflection Critic Agents, Ragas, DeepEval, Langsmith, Promptfoo, ROUGE BERTScore, ChromaDB, Supabase, Docker, GitHub Actions, Azure Container Apps, Koyeb, Vercel, Git, GitHub, Figma, Canva, ZodValidationPipe, RESTful API Design, LLM, N8n, Next.js, Pandas, Pinecone, PostgreSQL, Stripe Billing, Crew AI |

## What I'm looking for

```text
I’m looking to build agentic AI and LLM systems focused on reliable, observable behavior—multi-agent orchestration, grounded RAG, and rigorous evaluation. I want production deployment experience where measurement matters more than one-off demos.
```

## About

```text
I’m a final-year Computer Science student specializing in agentic AI systems, focused on building multi-agent LangGraph pipelines, RAG architectures, and fine-tuned LLMs. I enjoy going beyond demos by designing reliable, observable AI systems across healthcare and fintech domains.

I’m comfortable across the full stack for AI products—model fine-tuning and REST API design through production deployment and evaluation. I lean heavily into orchestration, evaluation, and observability, using tools like LangGraph, LangSmith, Ragas, and DeepEval to keep outputs grounded and measurable.

In my projects, I shipped an AI-powered SaaS with secure Supabase RLS and layered auth, built an agentic pharmacovigilance drug safety monitor with LangGraph + RAG grounded in cited sources, and developed an agentic trading pipeline with CrewAI and MCP-style tool decoupling. My goal is to keep iterating on agentic systems that are dependable in real-world conditions.
```

## Experience

### AI Pharmacovigilance Drug Safety Monitor

AI Pharmacovigilance Drug Safety Monitor. Jan 2026 - Present

```text
Built a 4-agent LangGraph pipeline to flag medication risks using structured patient data and grounded retrieval from OpenFDA, DrugBank Open, and PubMed. Fine-tuned Llama 3 with QLoRA on FAERS data and instrumented groundedness/hallucination scoring with Ragas/DeepEval before deploying a FastAPI backend and dashboard.
```

Skills: Python, LangGraph, fastAPI, ChromaDB, GROQ, LLaMA, QLoRA, OpenFDA, DrugBank-Open, PubMed, Sentence-Grounded-Evaluation, Ragas, DeepEval, Koyeb, Next.js

### Agentic Trading Intelligence System

Agentic Trading Intelligence System. Jan 2026 - Present

```text
Designed a multi-agent CrewAI trading pipeline with risk/critic agents that can veto flawed signals. Implemented a custom Model Context Protocol (MCP) server for market-data/broker tool access, added a backtesting framework, and deployed the system via Docker.
```

Skills: Python, Model-Context-Protocol-(MCP), Pandas, Multi-Agent-Systems, Custom-MCP-Server, Backtesting-Frameworks, Docker, Risk-Critic-Veto-Logic, Koyeb, Crew-AI

### AI-Powered Job Seeker SaaS

OutSauce. Jan 2025 - Present

```text
Shipped a TypeScript/NestJS SaaS for job seekers and freelancers with Supabase-backed authentication, authorization guards, and Zod validation. Built RLS-enforced PostgreSQL data access, Stripe 4-tier billing with webhooks, and n8n automation for role-gated admin dashboards.
```

Skills: TypeScript, NestJS, Next.js, Supabase, Stripe, N8n, REST-APIs, Zod, PostgreSQL, Webhooks, LinkedIn-Scraping

## Education

### COMSATS University Islamabad - Sahiwal Campus

BS Computer Science, Computer Science. 2022 - Present. Grade: CGPA: 3.7/4.00

```text
BS Computer Science student at COMSATS University Islamabad, Sahiwal Campus (ongoing), with a CGPA of 3.7/4.00.
```

## Tech stack

- Stripe Billing
- GitHub
- GitHub Actions
- NumPy
- Pandas
- PostgreSQL
- Gmail
- Next.js
- NestJS
- Tailwind CSS
- Figma
- scikit-learn
- FastAPI
- Vercel
- Canva
- SQL
- Supabase
- LangChain
- ChromaDB
- Weights & Biases
- AutoGen
- Pinecone
- CrewAI
- Groq
- DeepEval
- Koyeb
- Azure Container Apps
- Ragas
- N8N
- Agentic
- LangGraph
- LangSmith
- Promptfoo
- Model Context Protocol (MCP)
- PEFT
- Sentence Transformers

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

## People also viewed

- [Shahzaib Noor](https://himalayas.app/@shahzaibnoor): Senior Agentic AI Engineer, Independent Consulting
- [Awais User](https://himalayas.app/@awaishaneef): AI/ML Developer, Enliven AI
- [Shaheer Zaman](https://himalayas.app/@shaheerzaman): Agentic AI Engineer, Upwork
- [Hamad Maqsood](https://himalayas.app/@hamadmaqsood): AI/ML Engineer, IgniteTech (GFI Software)
- [Haseeb Wajid](https://himalayas.app/@haseebwajid): AI Systems Engineer, Alphabridge
- [Tayyab Hussain](https://himalayas.app/@tayyabhussain2): AI Engineer, Self Employed
- [Sbah Ud Din User](https://himalayas.app/@sbahuddinuser1): Lead AI Engineer, Edgec.io
- [Muneeb Ahmad](https://himalayas.app/@mxneeb): Project manager, Weave Designs
- [Umme Habiba](https://himalayas.app/@ummehabiba6): Marathon Faculty, Agentic AI, GIAIC
- [adina rehman](https://himalayas.app/@adinarehman): Freelance AI Agent Developer, Self Employed
