About
Data Scientist with 1 year of industry experience and a background in software development, specializing in machine learning, NLP, LLM applications, RAG and agentic AI. Experienced in Python, SQL, Pandas, NumPy, Scikit-learn, XGBoost, LangChain, LangGraph, FastAPI, MongoDB, FAISS and AWS. Delivered production AI workflows including high-throughput transcription pipelines, LLM-driven interview question generation, Financial RAG chatbots and automated data-analysis agents. Strong in data preprocessing, feature engineering, model development and orchestration of LLM-based systems; seeking roles in Data Science, Applied AI or ML Engineering.
Skills & Expertise (22)
Work Experience
Data Scientist
Tatras Data
Jan 2023 - Present
Built and evaluated a self-hosted Whisper Medium transcription pipeline using Python, Redis, Celery, and Docker to support a projected workload of 1,500 candidates and 750 hours of interview audio over 3 days. Performed infrastructure and cost analysis comparing self-hosted Whisper with Groq Whisper, identifying approximately 37% lower projected sprint cost while eliminating the need for 18 parallel Whisper servers. Migrated transcription inference to Groq Whisper Large v3 after latency evaluation, increasing processing throughput from ~0.6× real-time to 200×+ real-time. Built an LLM-driven candidate question-generation workflow using LangGraph to orchestrate candidate-data retrieval, resume parsing, question generation, and database updates. Designed category-specific interview question generation (icebreaker, resume-related, experience-related) using parsed candidate profiles. Integrated MongoDB for retrieval and persistence of candidate information and generated interview questions.
Associate Software Developer
Tatras Data
Jan 2023 - Feb 2023
Built and maintained production full-stack applications using React.js, Python, and FastAPI across frontend, backend APIs, data flow, and third-party integrations. Designed and implemented RESTful APIs handling data validation, business logic, and database interactions for production environments.
Education
B.Sc in Computer Science and Technology - PGDAV COLLEGE, Delhi
- · Afghanistan
12th - CISCE(ICSE/ISC), English
- · Afghanistan
10th - CISCE(ICSE/ISC), English
- · Afghanistan
Certifications
No certifications added yet
Interested in this developer?
Profile Score Breakdown
Profile Overview
Availability Details
Visa Status
Need Sponsorship
Relocation
Not Open to Relocation
Skills (22)
Click a skill to find developers with the same skill
