Principal Data/ML Engineer | AWS, Terraform | LLM/RAG, MLOps

Contact for pricing

About this service

Summary

Principal Data & ML Engineer specialising in AWS-native platforms, Terraform IaC and production LLM/RAG. I design and ship secure, observable AI systems—from data ingestion and vector search to Bedrock/SageMaker endpoints—backed by CI/CD, automated evaluation (RAGAS/ARES) and cost controls. HashiCorp Terraform Certified, with proven deliveries (e.g., DISMANTLE-AI, AWS Starter Pack), I provide clean code, clear docs and a smooth handover.

What's included

  • Production LLM/RAG API (AWS)

    A Bedrock/SageMaker endpoint with retrieval orchestration, ready for app integration.

  • Retrieval Pipeline & Vector Index

    Ingestion, chunking, embeddings and an indexed store (e.g., OpenSearch/pgvector).

  • Terraform Infrastructure (IaC)

    Modular Terraform for VPC, IAM, networking, compute, storage and policies.

  • CI/CD Pipelines (GitHub Actions)

    Build, test, security scans and deploy for app/model/IaC with environment promotion.

  • Data Pipelines (ETL/ELT)

    AWS-native ingestion and transformation jobs with schedules and retries.

  • Evaluation & Testing

    Automated quality checks (e.g., RAGAS/ARES), latency/cost tests and regression suite.

  • Observability & Cost Controls

    CloudWatch logs/metrics/dashboards, basic alerts, and AWS Budgets with tagging.

  • Security Baseline

    Least-privilege IAM, encryption in transit/at rest, secrets management and guardrails.

  • Architecture Pack

    High-level diagram, components list, data flow and decision log (ADRs).

  • Documentation & Handover

    README, runbooks, recorded walkthrough and a time-boxed post-delivery bug-fix window.


Skills and tools

Data Analyst

Data Engineer

Data Scraper

BeautifulSoup

BeautifulSoup

Python

Python

R

R

Scrapy

Scrapy

TensorFlow

TensorFlow

Industries

Artificial Intelligence
Data
IT Infrastructure