Open to opportunities

Aditya kumar Arya

@adityakumararya

Message

AI/ML engineer specializing in RAG, LLM fine-tuning, and production-ready generative AI solutions.

India

Message

What I'm looking for

I seek roles building production generative AI and RAG systems, emphasizing low-latency inference, measurable impact, and collaborative engineering teams.

I am an AI/ML engineer with hands-on experience building production generative AI systems, RAG pipelines, and knowledge-graph chatbots. I focus on low-latency, high-accuracy solutions and practical integrations with vector stores and downstream applications.

My work includes fine-tuning and optimizing LLMs using LoRA and quantization for faster inference, developing voice-enabled and semantic-search agents, and implementing OCR- and LLM-backed information extraction systems. I have delivered measurable improvements such as 25% inference performance gains and reductions in analyst workload by up to 60%.

I enjoy end-to-end system design—from data ingestion and vectorization to model tuning and deployment—and I actively contribute to projects that combine ML, NLP, and real-time integrations to deliver reliable, user-focused AI products.

Experience

Work history, roles, and key accomplishments

GenAI Intern

Ingenious E-Brain

Jun 2025 - Dec 2025 (6 months)

Developed AI/ML tools including an agentic AI, RAG pipeline, and knowledge-graph chatbot achieving 90% accuracy; fine-tuned LLMs with LoRA and quantization to improve inference performance by 25% and reduced analyst workload by 50–60% as technical advisor on a Data Intelligence product.

RAG Knowledge Graphs LoRAs Model Quantization Fine Tuned LLMs VectorDB fastAPI Python

AI/ML Engineer

RemoteEngine

Apr 2025 - Jun 2025 (2 months)

Built a book-search agent and AI developer search system using a RAG pipeline with MongoDB Atlas for semantic search; implemented a voice-enabled context-aware AI agent and reduced end-to-end latency by 2.74% versus a baseline.

RAG MongoDB Atlas Semantic Search Python VectorDB

Engineering Intern

LiquidMind AI

Feb 2025 - Mar 2025 (1 month)

Developed an invoice extraction system using OCR and multimodal LLMs (Goten OCR2, Ollama 3, Qwen2VL) and built a RAG model for TradeVeda to ensure accurate, relevant query results.

RAG Data Extraction Python NLP VectorDB

Education

Degrees, certifications, and relevant coursework

Indian Institute of Information Technology, Una

Bachelor of Technology, Information Technology

2022 -

Grade: CGPA: 7.46

Activities and societies: Technical projects in AI/ML (medical chatbot, VAE, stock analyzer); coding contest participation (CodeChef 3-star); extracurriculars: music and sports placements.

Pursuing B.Tech in Information Technology with coursework and projects focused on AI/ML, RAG, and full-stack development; current CGPA 7.46 (Nov 2022–Jun 2026).