Looking for a job

Ujjwal Khadka

@ujjwalkhadka

AI/ML Engineer specializing in Agentic AI, LLMs, and cloud (AWS) architecture. I build and deploy scalable, production-grade AI systems.

Nepal

Message

What I'm looking for

As a Data & Machine Learning Engineer, I look for several crucial aspects when working on projects or evaluating solutions. I focus on the accuracy and performance of models, ensuring they generalize well to new data. Robustness and reliability in production environments are key, along with interpretability and explainability to ensure results are understandable and actionable.

With over 3 years of experience working remotely with US-based tech companies, I specialize in architecting and deploying production-grade AI solutions. My core expertise lies in building advanced Retrieval-Augmented Generation (RAG) systems, Agentic Workflows, MCPs, and scalable NLP pipelines that drive operational efficiency.

Currently, as an LLM Engineer, I focus on the modern AI stack—leveraging LangChain, LangGraph, and Vector Databases (Pinecone, Chroma) to transform raw data into actionable intelligence. My background spans from optimizing Spark pipelines for healthcare data to deploying context-aware chatbots. I combine strong theoretical foundations in Biomedical Engineering with hands-on software engineering to build robust, interpretable, and high-performance AI systems.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer

Current

Genese Solutions

Apr 2025 - Present (9 months)

•Built and integrated machine learning and generative AI applications using AWS Bedrock, S3,
Lambda, CloudWatch, and Redshift.
•Contributed to multiple MCP-based projects.
•Led legal document processing initiatives leveraging large language models for document
understanding, classification, and information extraction.

Python AWS Agentic AI MCP (Model Context Protocol)LLM Integrations

LLM Engineer

Novelty Technology

Sep 2024 - Mar 2025 (6 months)

Built and deployed RAG-based AI chatbots and summarization pipelines, improving context-aware responses and information accessibility through vector search and optimized embeddings.

RAG Vector Databases Embeddings Summarization Python NLP Deployment

SparkNLP Fellow

John Snow Labs

Mar 2024 - Sep 2024 (6 months)

Developed and optimized NLP models for neurodegenerative disorder analysis, using PySpark to scale data handling and improve model performance for clinical datasets.

Pyspark NLP Optimization Scalability Data Processing

AI Engineer

Fusemachines

Sep 2023 - Mar 2024 (6 months)

Built RAG-based chatbots and summarization systems, optimizing document retrieval and contextual understanding through advanced embeddings and vector search techniques.

RAG Vector Search Embeddings Chatbot Summarization NLP Python Information Retrieval

Data Engineer Intern

Technocolabs Softwares

Jan 2023 - Sep 2023 (8 months)

Assisted in building scalable data warehousing and optimized data processing workflows to improve performance and deliver data-driven insights across teams.

Data Warehousing ETL Data Processing Python Performance Optimization Cross Functional Collaboration SQL Spark

Research Assistant

National Institute of Engineering and Technology

Mar 2022 - Aug 2023 (1 year 5 months)

Researched and implemented a comparative analysis of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) for detecting and classifying neurodegenerative disorders from medical images, including MRI, CT, and PET scans.

Python LLM Biomedical Data Sciences