Looking for a job

Dhaivat Jambudia

@dhaivatjambudia

Message

AI/ML Engineer | Python | AI Agent Developer | RAG | Deployment

India

Message

What I'm looking for

I seek hands-on roles building production LLM systems and multimodal agents with strong MLOps, scalable deployments, and opportunities to own architecture and product impact.

I am AI/ML engineer focused on building production-ready LLM systems, multimodal agents, and end-to-end MLOps pipelines. I design robust data ingestion, memory, and retrieval systems and deploy scalable services for real users.

My recent projects include architecting a multimodal WhatsApp AI agent with hybrid memory (SQLite + Qdrant), Groq LLaMA models, Eleven Labs TTS/STT, and vision/image generation, and building a Newton LLM via Airflow-driven ingestion, OpenAI embeddings, Qdrant, FastAPI, and Streamlit.

I combine practical MLOps practices—Docker, GitHub Actions, AWS deployments, and monitoring—with deep expertise in Python, PyTorch, LangChain, and vector databases to deliver reliable, user-facing AI products that emphasize context, memory, and scalability.

Experience

Work history, roles, and key accomplishments

Current

AI Agent Engineer

Current

Freelance

Aug 2025 - Present (2 months)

Developed a multimodal AI agent for WhatsApp integrating text, voice, image and vision capabilities with memory retention, scheduling, and location-aware responses, and architected hybrid memory using SQLite and Qdrant.

Python Groq LLaMA 3.3 Qdrant SQLite

LLM Engineer

Newton LLM

Feb 2025 - Apr 2025 (2 months)

Engineered an AI Twin of Isaac Newton by building a data ingestion pipeline with Apache Airflow, structuring knowledge in MongoDB, and implementing a RAG pipeline with OpenAI embeddings and Qdrant for context-aware responses.

Apache Airflow MongoDB Qdrant Embeddings RAG fastAPI Streamlit Data Pipelines

Machine Learning Engineer

Freelance

Dec 2024 - Jan 2025 (1 month)

Developed and deployed an insurance churn prediction solution with CI/CD, Docker containerization, and AWS deployment, orchestrating the full MLOps lifecycle including monitoring and automated retraining.