Artificial Intelligence Engineer

Job Title: AI/ML Engineer – Regulatory Compliance

Experience: 5+ years

Location: Remote

About the Role

AI/ML Engineer

Key Responsibilities

• Develop and deploy

  AI solutions for regulatory compliance

  using

  AWS Bedrock and LLMs

  .
• Build parsing and chunking strategies for diverse data sources (

  files, APIs, newsletters, email lists, web pages

  ).
• Embed documents into

  vector databases

  with additional metadata for retrieval efficiency.
• Manage and maintain

  vector databases

  (Qdrant, OpenSearch) ensuring scalability and reliability.
• Design and implement

  RAG systems

  , experimenting with

  prompt engineering

  for optimized responses.
• Integrate

  AWS Bedrock and LLM APIs

  into enterprise systems.
• Monitor, evaluate, and optimize

  RAG model performance

  .
• Design and implement

  secure and scalable data storage solutions

  for regulatory datasets.
• Ensure

  data integrity, security, and availability

  across storage and pipelines.
• Optimize

  database performance and scalability

  .
• Manage and experiment with

  MLOps workflows

  using

  AWS SageMaker

  .

Required Skills & Experience

• 5+ years of experience

  in AI/ML engineering or applied data science.
• Strong hands-on expertise with

  Vector Databases

  (Qdrant, OpenSearch).
• Proficiency in

  Python

  (preferred) and

  JavaScript

  for system integrations.
• Strong SQL skills and experience with

  PySpark

  for large-scale data handling.
• Experience with

  AWS Bedrock, SageMaker, and cloud-based ML workflows

  .
• Familiarity with

  Jupyter Notebooks

  for prototyping and experimentation.
• Strong understanding of

  RAG architectures, prompt engineering, and LLM integration

  .
• Knowledge of

  data storage, optimization, and security best practices

  .
• Strong problem-solving and debugging skills.

Nice to Have

• Experience with

  regulatory or compliance-related data platforms

  .
• Exposure to

  LangChain, LlamaIndex, or similar frameworks

  .
• Knowledge of

  Kubernetes/Docker

  for ML deployment.
• Familiarity with

  observability and monitoring tools

  for ML pipelines.