Data AI Engineer

Company Description Dimensionless Technologies is a global IT consultancy and AI services company that builds AI-driven solutions for clients across multiple industries. Founded in 2016 in Mumbai, India, the company focuses on transforming businesses by improving operational efficiency and driving growth through artificial intelligence. The team includes data scientists, machine learning engineers, and software developers who design and deploy tailored solutions such as security automation, fraud detection, and natural language processing. Dimensionless operates from key global locations, including offices in New Jersey and Mumbai, serving a diverse international clientele. The company emphasizes innovation, technical excellence, and close collaboration with clients to meet their unique business needs.

We are looking to hire a Senior Data Engineer with experience in building Agents on AWS ecosystem.

Key Responsibilities:

1. Data Engineering & AWS Pipelines

• Design and develop scalable data pipelines for ingesting data from REST APIs, databases, files and other enterprise data sources.
• Build data ingestion and transformation workflows using Python, PySpark and AWS Glue.
• Orchestrate pipelines using AWS Step Functions and other appropriate AWS services.
• Design S3-based data layers for raw, processed and curated data.
• Create and maintain Athena/Glue Catalog layers for querying and downstream consumption.

2. Backend & API Development

• Design and develop Python-based backend services and REST APIs
• Build microservices that can be consumed by AI agents and front-end applications.
• Develop integrations with enterprise systems and third-party APIs.
• Implement authentication, validation, error handling, logging and monitoring.
• Containerize and deploy backend services using appropriate AWS/cloud technologies.

3. AI Agent Development

• Design and build AI agents using Amazon Bedrock, AgentCore and Strands.
• Develop agents capable of interacting with enterprise data, APIs and backend services.
• Implement agent tools/function calling, workflows, context/state management and RAG where appropriate.
• Integrate LLMs with enterprise applications and data sources.
• Apply appropriate practices for prompt management, evaluation, security, observability and cost optimization.
• Develop reusable agent frameworks and components that can support multiple enterprise AI use cases.

4. Pro-Code Engineering & DevOps

• Develop solutions using clean, modular, reusable and testable code.
• Use Git and CI/CD practices for source control, code reviews and deployments.
• Follow configuration-driven development using YAML/JSON and environment-specific configuration.
• Have a good understanding of Infrastructure as Code (IaC) and cloud deployment practices.
• Terraform experience is preferred, particularly for provisioning and managing AWS infrastructure, but deep Terraform expertise is not mandatory.
• Follow enterprise standards around security, secrets management, logging, monitoring and access control.

REQUIREMENTS

Must Have

• Strong hands-on Python development experience.
• Strong AWS development experience.
• Hands-on experience building data pipelines / ETL processes.
• Experience with PySpark and preferably AWS Glue.
• Experience with S3 and Athena or equivalent cloud data-lake technologies.
• Experience with workflow orchestration such as AWS Step Functions.
• Experience developing REST APIs and backend services
• Hands-on experience developing LLM/GenAI applications or AI agents.
• Experience with Amazon Bedrock.
• Exposure to AgentCore and/or Strands is highly desirable.
• Strong understanding of Git, software engineering practices and CI/CD