AI Engineer

Role Summary

We are looking for an experienced and hands-on AI Data Engineer to design, develop, and operationalize secure, scalable, production-grade Generative AI, agentic AI, and cloud data solutions.

The successful candidate will combine strong AI engineering capabilities—including large language models, prompt engineering, retrieval-augmented generation, vector search, AI agents, and LLMOps—with a solid foundation in Python, advanced SQL, databases, and cloud-based data engineering.

The candidate should be also be able to work in establishing data pipelines and engineering—from data ingestion and preparation, to data modeling, deployment and monitoring.

AI & Data Engineer

·Design, build, and operate secure, scalable, production-grade Generative AI, agentic AI, and cloud data solutions for analytics and reporting.

·Develop LLM applications for analytics and reporting using prompt engineering, retrieval-augmented generation (RAG), embeddings, vector search, structured outputs, tool calling, function calling, fine-tuning, and model routing.

·Build AI agents that retrieve enterprise data, use approved tools and APIs, coordinate multi-step workflows, and operate within defined guardrails and human oversight.

·Integrate foundation models, AI agents, enterprise data platforms, APIs, workflow orchestration tools, document repositories, and reporting applications.

·Develop AI capabilities such as natural-language querying, conversational analytics, automated summaries, intelligent recommendations, anomaly detection, narrative reporting, and workflow automation.

·Design, develop, and maintain robust ETL/ELT pipelines for structured and unstructured data across data lakes, warehouses, and lake houses.

·Design serverless, event-driven, and cost-efficient cloud architectures using a primary cloud platform such as AWS, Azure, or GCP.

·Develop data models, data-quality frameworks, validation rules, metadata, lineage, and reusable data products.

·Build production-grade services using Python, SQL, APIs, CI/CD, automated testing, infrastructure as code, and observability practices.

·Apply responsible AI practices, including data privacy, security, access control, content safety, prompt-injection protection, and prevention of sensitive-data leakage.

·Deploy AI solutions using services such as Amazon Bedrock, Amazon SageMaker, Azure OpenAI, Azure AI Foundry, Google Vertex AI, OpenAI APIs, vector databases, and enterprise search platforms.

·Develop and orchestrate data workflows using AWS Glue, Glue Workflows, AWS Lambda, Step Functions, Amazon S3, Athena, Redshift, and Amazon RDS.

·Partner with data, technology, and business stakeholders to translate requirements into data models, AI features, visualizations, and actionable insights.

Mandatory Technical Skills

AI and Generative AI

·Strong understanding of Generative AI and large language model concepts.

·Hands-on experience developing LLM-based applications.

·Practical experience with:

oPrompt engineering and prompt templates

oRetrieval-augmented generation

oEmbeddings and semantic search

oVector search and vector databases

oDocument ingestion and chunking

oStructured LLM outputs

oContext and conversation management

oAI-agent development

oMulti-step agentic workflows

oModel evaluation and response validation

Programming

·Strong hands-on programming experience in Python.

·Good understanding of object-oriented programming, data structures, exception handling, logging, API integration, and asynchronous processing.

·Experience with relevant Python libraries and frameworks, such as:

oPandas

oPySpark

oBoto3

oFastAPI or Flask

oLangChain

oLangGraph

oLlamaIndex

SQL, Databases and Data Engineering

·Strong proficiency in writing and optimizing advanced SQL queries.

·Hands-on experience with complex joins and subqueries, Window and analytical functions and stored procedures

Preferred Technical Skills

·Exposure to business intelligence and reporting tools, particularly Microsoft Power BI or Tableau