I build RAG pipelines, fine-tune domain models, and deploy secure LLM applications on Google Cloud. My engineering focus centers on turning machine learning research into production-grade systems—from vectorized indexing and semantic retrieval to high-throughput containerized serving.
Currently completing my third year in B.Tech Artificial Intelligence & Data Science (GGSIPU, India). I approach software through practical, end-to-end implementation and reproducible benchmarks.
Status: Seeking AI/ML engineering internships · Open to select freelance projects.
CURRENT FOCUS
├── RAG Systems : Hybrid dense/sparse retrieval, context reranking, latency optimization
├── Deployment : Cloud Run microservices, Docker containerization, verified auth gates
└── Evaluation : Automated LLM benchmarking harnesses, semantic drift metrics
A selection of practical applications and evaluation systems deployed with containerized backends:
|
Repository: github.com/OjasPal/ML-DL-Portfolio |
Repository: github.com/OjasPal/Personal-Gemini-Journal |
|
Repository: github.com/OjasPal/Medical-RAG-Chatbot |
Repository: github.com/OjasPal/EvalAI |
Curated technologies verified across my active repositories and deployments:
| Category | Core Technologies |
|---|---|
| Languages | Python · C++ |
| GenAI & RAG | LangChain · Pinecone · Groq API · Gemini API · Ollama · HuggingFace |
| Machine Learning | PyTorch · Scikit-Learn · Computer Vision · NLP · Pandas |
| Cloud & Deployment | Google Cloud Run · Cloud Firestore · Firebase Auth · FastAPI · Streamlit |
| Developer Tools | Git & GitHub · VS Code · Jupyter Notebook |
Building something with LLMs, RAG, or looking for an AI/ML engineering intern?
• Portfolio: ojaspal.github.io
• Email: ojaspal.dev@gmail.com
• LinkedIn: linkedin.com/in/ojas-pal
• GitHub: github.com/OjasPal