GenAI Data Automation Engineer – Distant with quarterly journey to DC – Protos IT – Distant

Data Automation Engineer This is a totally distant, teleworking place with potential journey to the Washington D.C. metro space on particular events.
Ability to acquire Public Trust clearance.

Job Description

Leidos is looking for a Data Automation Engineer to design and implement modern, AI-driven automation options throughout AWS and Azure hybrid environments. You shall be liable for constructing clever, scalable information pipelines and automations that combine cloud providers, enterprise instruments, and Generative AI to assist mission-critical analytics, reporting, and buyer engagement platforms. Ideal candidate is mission targeted, supply oriented, applies crucial pondering to create modern features and remedy technical points.

In this position, you’ll:

• Design and preserve information pipelines in AWS utilizing S3, RDS/SQL Server, Glue, Lambda, EMR, DynamoDB, and Step Functions.
• Develop ETL/ELT processes to maneuver information from a number of information techniques together with DynamoDB SQL Server (AWS) and between AWS Azure SQL techniques.
• Integrate AWS Connect CRM information into the enterprise information pipeline for analytics and operational reporting.
• Engineer, improve ingestion pipelines with Apache Spark, Flume, Kafka for real-time and batch processing into Apache Solr, AWS Open Search platforms.
• Leverage Generative AI providers and Frameworks (AWS Bedrock, Amazon Q, Azure OpenAI, Hugging Face, LangChain) to:

o Create automated processes for vector era and embeddings from unstructured information.

o Automate information high quality checks, metadata tagging, and lineage monitoring.

o Enhance ingestion/ETL with LLM-assisted transformation and anomaly detection.

o Build conversational BI interfaces that enable pure language entry to Solr and SQL information.

• Develop AI-powered copilots for pipeline monitoring and automatic troubleshooting.
• Implement SQL Server saved procedures, indexing, question optimization, profiling, and execution plan tuning to maximise efficiency.
• Apply CI/CD finest practices utilizing GitHub, Jenkins, or Azure DevOps for each information pipelines and GenAI mannequin integration.
• Ensure safety and compliance by way of IAM, KMS encryption, VPC isolation, RBAC, and firewalls.
• Support Agile DevOps processes with sprint-based supply of pipeline and AI-enabled options.

Required Qualifications:

• BS in Computer Science or associated area with 2+ years of knowledge engineering, automation experiences.
• Hands-on expertise with SQL, SSIS, Python, Spark, Bash, Power shell, AWS/Azure CLIs.
• Experience with AWS providers like S3, RDS/SQL Server, Glue, Lambda, EMR, DynamoDB.
• Familiarity with Apache Flume, Kafka, Solr for large-scale information ingestion and search.
• Familiarity with LLM, Gen AI frameworks utilizing AWS Bedrock, Azure OpenAI or open supply platform, instruments.
• Experience with integrating REST API calls in information pipelines and workflows.
• Familiarity with JIRA, GitHub / Azure DevOps / Jenkins for SDLC and CI/CD automation.
• Strong troubleshooting and efficiency optimization abilities in SQL, Spark or different information engineering options.
• Experience operationalizing Generative AI (GenAI Ops) pipelines, together with mannequin deployment, monitoring, retraining, and lifecycle administration for LLMs and AI-enabled information workflows.
• Good communication and presentation abilities.