Python Developer - AWS, AI, LLM
Hybrid - Reston, VA OR Washington, DC
Description:
This position is on site at RTC or MTC.
Design, develop, and maintain scalable data pipelines and ETL/ELT processes using Python and SQL.
Develop and optimize complex SQL queries, stored procedures, and database objects to support reporting, analytics, and AI-driven use cases.
Perform source-to-target data mapping and execute comprehensive data quality validation to ensure data integrity, accuracy, and consistency.
Work with AWS data services, including AWS Lambda, Amazon Redshift, Apache Iceberg, and Amazon Glacier, to build and support scalable cloud-based data solutions.
Design and develop data pipelines that prepare, transform, and deliver structured and unstructured data for Generative AI and Large Language Model (LLM) applications.
Develop and integrate Generative AI solutions using LLMs, including prompt engineering, model/API integration, and retrieval-based applications.
Support the implementation of Retrieval-Augmented Generation (RAG) solutions by preparing enterprise data, generating embeddings, and integrating vector databases or semantic search capabilities.
Integrate Generative AI models and services through APIs and cloud-based AI platforms, including Amazon Bedrock or equivalent LLM platforms.
Apply prompt engineering and prompt optimization techniques to improve the accuracy, reliability, and consistency of LLM-generated responses.
Evaluate GenAI outputs using appropriate quality metrics and testing approaches, including relevance, groundedness, accuracy, and hallucination detection.
Implement appropriate AI security, data privacy, governance, and responsible AI controls when working with enterprise data and Generative AI solutions.
Collaborate with business stakeholders, data analysts, developers, and AI/ML teams to understand business requirements and translate them into scalable technical solutions.
Develop, execute, and maintain automated and manual test cases for data validation, ETL processes, reporting solutions, and GenAI-enabled applications.
Create and maintain technical documentation, including design documents, mapping documents, data dictionaries, AI solution architecture, prompt documentation, and operational procedures.
Track work items, defects, and enhancements using JIRA and contribute to continuous process improvements.
Required Qualifications
3 5 years of experience in data engineering, software development, data analytics, or a related technical field.
Strong programming experience in Python.
Advanced proficiency in SQL, including complex query development, data transformation, and performance optimization.
Hands-on experience designing and developing ETL/ELT pipelines and data processing solutions.
Strong knowledge of relational databases, data modeling, and database design principles.
Hands-on experience with AWS services, particularly data processing, storage, serverless, and analytics technologies.
Working knowledge of Generative AI, Large Language Models (LLMs), and prompt engineering.
Experience integrating LLMs through APIs or managed AI platforms such as Amazon Bedrock, Azure OpenAI, OpenAI APIs, or similar technologies.
Understanding of Retrieval-Augmented Generation (RAG), embeddings, vector databases, and semantic search concepts.
Familiarity with techniques for evaluating and testing GenAI applications, including groundedness, relevance, hallucination detection, and response quality.
Understanding of responsible AI, data security, privacy, and governance considerations associated with enterprise Generative AI applications.
Preferred Qualifications
Experience building production-grade RAG or enterprise knowledge-assistant solutions.
Familiarity with AI agents, tool/function calling, and agentic workflows.
Experience applying Generative AI to data engineering use cases such as data discovery, metadata generation, data quality analysis, SQL generation, document processing, and analytics automation.
