Skip to content
Hemz.
0%

Skills

AI engineering, end to end.

8+ years building the parts of AI that have to work every day: agents, the observability to trust them, and the MLOps to ship them, plus everything underneath.

head 0.0 · previous-token

Agentic Solutions

Multi-agent systems that plan, use tools, and hold up in production, not just in the demo.

  • LangChain
  • LlamaIndex
  • CrewAI
  • MCP
  • Bedrock AgentCore
  • Tool use
  • Multi-agent orchestration

head 1.3 · induction

Observability Platforms

Tracing, evaluation, and guardrails that make every step an agent takes visible and debuggable.

  • OpenTelemetry
  • Arize Phoenix
  • Langfuse
  • SigNoz
  • LLM evaluation
  • Guardrails

head 2.7 · attention-sink

MLOps & LLMOps

Paved roads from experiment to production: CI/CD, retraining, deployment, and drift monitoring.

  • Databricks
  • Azure ML
  • Azure DevOps
  • CI/CD
  • Model versioning
  • Evaluation gates
  • Drift monitoring

deployed inretailhealthcarecpg

→The full stack

Drawn like a model.

Layers from infrastructure up to agents, read bottom to top like a forward pass. Observability and MLOps aren't layers: they're the side streams that run through all of them.

  1. L6

    Agentic Solutions

    Multi-agent systems that plan, use tools, and hold up in production, not just in the demo.

    • LangChain
    • LlamaIndex
    • CrewAI
    • MCP
    • Bedrock AgentCore
    • Tool use
    • Multi-agent orchestration
  2. L5

    RAG & Retrieval

    Retrieval pipelines that ground LLMs in private data, with memory and chat history.

    • LangChain
    • LlamaIndex
    • Qdrant
    • Pinecone
    • FAISS
    • Redis
  3. L4

    LLMs & Fine-tuning

    Choosing, prompting, and fine-tuning models to fit the task and the budget.

    • Fine-tuning
    • Prompt engineering
    • Llama 3
    • Claude
    • Local LLMs
  4. L3

    Vision & Audio

    Models that see and listen: image recognition, transcription, and summarization.

    • Image classification
    • EfficientNetV2
    • Speech-to-text
    • Summarization
    • Streamlit
  5. L2

    ML & Deep Learning

    From classical models to deep nets, trained and shipped as real services.

    • Classical ML
    • Deep learning
    • Transfer learning
    • Random Forest
  6. L1

    Data Engineering

    Data-centric pipelines that feed models clean, trustworthy data at scale.

    • Python
    • Spark
    • Databricks
    • SQL
    • Data pipelines
  7. L0

    Cloud & DevOps

    Azure first, AWS and GCP when the problem calls for them, all automated.

    • Azure AI Services
    • AWS
    • GCP
    • Containers
    • CI/CD

Observability Platforms

Tracing, evaluation, and guardrails that make every step an agent takes visible and debuggable.

  • OpenTelemetry
  • Arize Phoenix
  • Langfuse
  • SigNoz
  • LLM evaluation
  • Guardrails

MLOps & LLMOps

Paved roads from experiment to production: CI/CD, retraining, deployment, and drift monitoring.

  • Databricks
  • Azure ML
  • Azure DevOps
  • CI/CD
  • Model versioning
  • Evaluation gates
  • Drift monitoring