Skip to content
View mastroke's full-sized avatar
3 followers · 1 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Shark

Block or report mastroke

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mastroke/README.md

Masoob Alam

🧠 Building production-grade AI agents

I build agentic AI systems the way production infrastructure should be built composable architectures with explicit state, durable memory, evaluation gates, and deployment boundaries that hold under load. The hard part of agentic AI isn't the model; it's the seams.

  • 🔭 I'm currently building memory-layer and acceptance tooling for AI agents
  • 👯 I'm looking to collaborate on agent memory, evaluation, and quant infrastructure
  • 🤔 I'm looking for help with scaling eval harnesses across prompt, tool, and memory layers
  • 💬 Ask me about agentic AI, MLOps, memory architecture, and quantitative systems
  • 📫 How to reach me: LinkedIn · GitHub
  • 😄 Pronouns: he/him
  • ⚡ Memory is a contract, not a transcript dump.

Topics: agentic-ai · mlops · quantitative-finance · llm-agents · memory · evaluation

Pinned Loading

  1. agentic-mlops-foundry agentic-mlops-foundry Public

    Production template for agentic AI services with eval gates, Docker, FastAPI and CI.

    Python

  2. agentic-quant-lab agentic-quant-lab Public

    Agentic quantitative research lab with risk guardrails, reproducible backtests and paper-trading boundaries.

    Python

  3. llm-finetuning-eval-lab llm-finetuning-eval-lab Public

    Reproducible fine-tuning and evaluation workflow for LLM classification tasks.

    Python

  4. memory-layer-rnd memory-layer-rnd Public

    Research harness for persistent memory layers in AI agents: episodic, semantic and graph memory.

    Python

  5. graphiti graphiti Public

    Forked from getzep/graphiti

    Build Real-Time Knowledge Graphs for AI Agents

    Python

  6. RLtrading RLtrading Public archive

    Agentic quantitative research lab with risk guardrails, reproducible backtests and paper-trading boundaries.

    Python