Transforming AI research into production systems that drive business value.
I’m Mohammad Shojaei, a Machine Learning Engineer with a particular focus on Large Language Models and Natural Language Processing. My professional interests revolve around translating cutting-edge research into robust, real-world systems. I spend considerable time refining training pipelines, optimizing inference for low latency, and fine-tuning models to effectively handle multiple languages. The field is dynamic and often unpredictable, but my central objective remains consistent: transforming theoretical concepts into production-grade tools that provide tangible value.
Currently, my primary work involves evaluating the latest open-source LLMs, with an emphasis on those touting comprehensive support for Persian. Keeping pace with the influx of new research is essential to ensuring my systems retain a competitive advantage.
-
My projects include architecting agentic systems with advanced reasoning capabilities, developing conversational audio agents resilient to unexpected queries, and contributing to open-source initiatives aimed at advancing AI accessibility for underrepresented languages.
-
In terms of professional development, I am consistently refining my understanding of AI agent design and evaluation, delving into technical aspects such as tool-calling and structured outputs, and exploring recent post-training methods to enhance the performance of models under 10B parameters.
-
If you wish to discuss advances in NLP, debate the rationale behind embedding dimensions, or exchange insights on deploying models to production environments, I welcome the opportunity for collaboration and knowledge sharing.
Languages & Core Libraries:
LLM & NLP Ecosystem:
Frameworks & Tools:
Thanks for dropping by! Let's connect and whip up something awesome.