Yassir Salmi

AI and Software Engineering at Oracle Labs

Work Experience


Software Engineer · Oracle Labs
Aug 2025 – present

I work as an AI Engineer at Oracle Labs, focusing on the evaluation and reliability of LLM-powered agents. My work includes contributing to the development of agentic applications and evaluation for AI systems.

Software Engineer, Intern · Oracle Labs
Feb 2025 – Jul 2025

As an AI Engineering Intern, I worked on the performance and deployment side of large language models. I benchmarked inference engines across a range of open-source models and hardware configurations, profiled serving systems to identify bottlenecks, and evaluated optimization techniques that significantly improved latency and throughput. The work helped guide production infrastructure decisions and deepen the team's understanding of efficient LLM serving.

Software Engineer, Intern · Oracle Labs
Jul 2024 – Oct 2024

I joined Oracle Labs as a Software Engineering Intern on Data Studio, an internal enterprise data science platform. My main role was integrating an AI assistant that allowed users to interact with data through natural language.

Open Source


NL2Analytics-View SQL Benchmark

GitHub

Contributed to Oracle's official public benchmark for evaluating LLM and agentic NL2SQL systems on generating Oracle Analytic View SQL. Contributed Analytic View schema/DDL artifacts, gold NL-to-SQL question sets, and agent evaluation specs comparing AV-specialized vs. vanilla agents.

Oracle Database, Analytic Views, Open Agent Spec, NL2SQL

Research


Experimental Evaluation and Benchmarking of Large Language Model Inference Engines (vLLM, llama.cpp, SGLang, etc.)

Ibn Zohr University · Oracle LabsFeb 2025 – Jul 2025

Master's thesis conducted at Oracle Labs investigating the comparative performance of LLM inference engines. Benchmarked +5 LLM inference engines (vLLM, SGLang, ONNX Runtime GenAI, llama.cpp, etc.) on open source models like Llama, Mistral, phi across CPU and GPU hardware, evaluating latency, throughput, and memory utilization under real-world workloads (summarization, RAG, NER, Q&A, ...). Profiled inference pipelines using NVIDIA Nsight Systems and Linux perf/flame graphs to identify kernel-level bottlenecks. Findings informed production infrastructure decisions on inference engine selection and prompt engineering strategies.

LLMs, vLLM, ONNX Runtime GenAI, SGLang, llama.cpp, inference benchmarking, PagedAttention, prefix caching, GPU/CPU profiling, suffix decoding, speculative decoding

Projects


RAG-Based Document Q&A System

GitHub

Built a RAG pipeline for Q&A over PDFs with pluggable embeddings/LLMs, incremental ingestion, and RAGAS-based evaluation.

Python, FastAPI, React, LangChain, ChromaDB

Paper Recommender Agent

GitHub

Built a Plan-and-Execute LLM agent for research paper discovery and structured deep-dive analysis across arXiv, Hugging Face, and Semantic Scholar.

Python, LangChain, Pydantic v2, arXiv API, pdfplumber, Hugging Face Hub

Skills


ProgrammingPython, Java, C, C++
Machine LearningData Cleaning and Preprocessing, Data Visualization, Regression, Classification, Clustering, Neural Networks (CNN, RNN, LSTM, GRU)
ToolsShell, Git, Docker/Podman, VS Code, IntelliJ IDEA, Jupyter Notebook, Agile Development
LanguagesEnglish (Proficient), French (Proficient), Arabic (Native)

Education


Master of Science in Data Science

Oct 2023 – Jul 2025
Ibn Zohr University – Agadir, Morocco
Relevant Coursework: Statistics & Probability, Machine Learning, Deep Learning, Computer Vision, Big Data
Thesis: Experimental Evaluation and Benchmarking of Large Language Model Inference Engines (vLLM, llama.cpp, SGLang, etc.)

Bachelor of Science in Computer Science

Sep 2020 – Jul 2023
Ibn Zohr University – Agadir, Morocco
Relevant Coursework: Data Structures & Algorithms, C, C++, Web Development(HTML, CSS, JS), Java, RDBMS