Application Developer @ IBM

Building production GenAI on AWS at IBM.

At IBM I integrate large language models into enterprise applications — retrieval-augmented generation, AI guardrails, and model tuning — on a serverless AWS stack, shipped through a disciplined CI/CD pipeline.

Retrieval-augmented generation
Queryuser question RetrievalRAG · embeddings Amazon BedrockClaude — the LLM Guardrailsvalidate · on-policy Responsegrounded answer
A standard RAG pipeline — built on AWS Lambda, Amazon Bedrock, S3 and DynamoDB.
  1. 01

    Generative AI integration

    Integrating large language models — Amazon Bedrock and Anthropic Claude — into enterprise applications, with multiple retrieval strategies and an extended-reasoning mode.

    • Bedrock
    • Claude
    • LLM
  2. 02

    Retrieval-augmented generation

    RAG over domain knowledge bases — embeddings and semantic retrieval with content segregation by business function — for grounded, relevant answers.

    • RAG
    • Embeddings
    • Knowledge bases
  3. 03

    AI guardrails & validation

    Automated validation with feedback loops keeps model outputs accurate, safe and on-policy — turning probabilistic models into dependable workflows.

    • Guardrails
    • Validation
    • Reliability
  4. 04

    Model tuning & prompt engineering

    Migrating and tuning models with dynamic prompt configurations and evaluation — getting the right behaviour from the right model for each market.

    • Prompt eng.
    • Tuning
    • Evaluation
  5. 05

    Serverless AWS backend

    Python on AWS Lambda with S3, DynamoDB, SQS and API Gateway — scalable, event-driven services powering the AI features behind the scenes.

    • Lambda
    • DynamoDB
    • S3
    • SQS
  6. 06

    CI/CD & delivery

    Shipping through a disciplined pipeline — Jenkins, SonarQube and JFrog — with Git branching across development, QA and production.

    • Jenkins
    • SonarQube
    • JFrog
    • Git

Curious about the rest of the stack?

See my full background, experience and skills — or get in touch directly.

About me Get in touch