We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowMy name is Usman S. and I have over 2 years of experience in the tech industry. I specialize in the following technologies: Large Language Model, Prompt Engineering, Retrieval Augmented Generation, LoRa, LangChain, etc.. I hold a degree in Master of Business Administration (MBA). Some of the notable projects I've worked on include: LLM/RAG Evaluation Framework, Domain‑Specific LLM Assistant Using Instruction Tuning, Document Ingestion & Chunking Pipeline for Large Scale Knowledge, Semantic Search Engine Using Embeddings & Vector Databases, Instruction‑Tuned Dataset Creation for LLMs, etc.. I am based in Toronto, Canada. I've successfully completed 10 projects while developing at Softaims.
I am a dedicated innovator who constantly explores and integrates emerging technologies to give projects a competitive edge. I possess a forward-thinking mindset, always evaluating new tools and methodologies to optimize development workflows and enhance application capabilities. Staying ahead of the curve is my default setting.
At Softaims, I apply this innovative spirit to solve legacy system challenges and build greenfield solutions that define new industry standards. My commitment is to deliver cutting-edge solutions that are both reliable and groundbreaking.
My professional drive is fueled by a desire to automate, optimize, and create highly efficient processes. I thrive in dynamic environments where my ability to quickly master and deploy new skills directly impacts project delivery and client satisfaction.
Main technologies
2 years
1 Year
1 Year
1 Year
Potentially possible
NeuroLayer Technologies
Built an evaluation framework to benchmark LLM and RAG outputs using accuracy, grounding, relevance, and hallucination metrics. Automated comparisons of retrievers and model settings, generating struc
Created a domain specialized assistant using instruction tuning and SFT datasets. Curated industry data, applied LoRA/qLoRA fine tuning, evaluated outputs, and delivered a model with improved accuracy
Built a complete ingestion pipeline for PDFs, DOCX, HTML, and text. Applied normalization, cleaning, deduplication, and token‑aware chunking. Added metadata tagging and prepared high quality chunks re
Developed a semantic search system using embeddings and vector databases (FAISS/Weaviate). Designed indexing, similarity retrieval, reranking, and metadata filters to deliver accurate, meaning based s
Created a high quality instruction dataset for fine‑tuning, including extraction, cleaning, deduplication, and formatting into SFT pairs. Generated synthetic samples, improved balance, and prepared ev
Master of Business Administration (MBA) in Computer science
2001-01-01-2004-01-01