1000000855.AI ENGINEER II.INFO TECH - DATA AND AI

Designs and maintains robust AI agents and data pipelines. Performs data

orchestrations and supports enterprise AI and Data efforts. Works across

departments to build scalable AI solutions that ensure reliable, secure, and

high-quality data is available to business users, analysts, upstream and

downstream applications. Responsible for the full lifecycle of AI Development –

from selecting foundation models (FM’s) to deploying scalable orchestration

layers on hybrid cloud environments. Contributes to data labelling, MLOps

integration, AI Observability, Language Models testing, and documentation in

collaboration with AI analysts, AI Architects, data scientists, developers, and

system owners.

RESPONSIBILITIES

Designs, develops, and maintains scalable AI Agents and Orchestration workflows

across structured and semi-structured data sources. Ensures consistent design

and delivery of data and AI platforms supporting Data Engineering, Cloud, and AI

centers of excellence. Integrates internal and external data sources with

enterprise data platforms, lakes, or warehouses. Designs and develops

multi-agent systems using frameworks like LangGraph, CrewAI, or Amazon Bedrock

to automate complex enterprise reviews and workflows. Performs data profiling,

cleansing, and standardization to improve data quality. Monitors data pipeline

health and troubleshoots failures or anomalies. Documents AI architecture, APIs,

AI Business rules, and data logic for internal users. Collaborates with DevOps

or infrastructure teams to implement automated AI processing workflows.

Collaborates with Enterprise Architecture teams to ensure AI solutions align

with internal policies, vendor questionnaires, and ethical AI guidelines.

Maintains data access controls, validation rules, and retention policies.

Translates business and AI requirements into technical specifications and AI

pipeline designs. Participates in Agile planning, backlog grooming, and

technical design sessions. Develops data and AI flow diagrams, Machine learning

models, and transformation logic. Supports dataset design and delivery for

dashboards, reports, or self-service analytics. Collaborates with application

owners to understand source system structures and data changes. Contributes to

solution architecture decisions related to Language model performance, security,

storage, and data delivery. Assists in scoping and estimating new data

initiatives and enhancement requests. Identifies reuse opportunities for data

components, tools, or models. Builds in validation and error-handling logic into

data and AI pipelines to support reliability. Performs root cause analysis for

data inconsistencies and recommends preventive actions. Contributes to and

follows testing procedures for data validation, performance, and integrity.

Implements version control, data lineage, and reproducibility practices.

Identifies performance bottlenecks and refactor inefficient data processes.

Recommends improvements to schema design, data granularity, and source-system

integration. Maintains awareness of industry standards for data governance,

security, and accessibility. Supports automation of routine data workflows and

manual reporting processes. Works closely with analysts, data scientists,

application developers, and stakeholders to deliver high-quality datasets.

Coordinates with system owners and system administrators to manage source data

access and schema changes. Supports QA and testing teams by validating expected

output and data quality criteria. Participates in data and AI design reviews,

standups, retrospectives, and sprint demos. Communicates technical limitations

or trade-offs to business stakeholders in an understandable way. Partners with

cybersecurity teams to ensure sensitive data is handled securely and in

compliance with County policy. Continues building technical proficiency in cloud

platforms, big data tools, and AI frameworks. Stays current with trends in data

engineering, streaming pipelines, and ML Ops practices. Contributes to internal

wikis, playbooks, and best practices documentation. Mentors junior data

engineers or interns on development and testing practices. Participates in

knowledge-sharing sessions, communities of practice, or hackathons. Proactively

seeks opportunities for cross-training with related disciplines (e.g., AI, Big

Data, DevOps and MLOps). Implements robust LLM engineering practices using tools

like Langfuse or Weights & Biases for tracing, debugging, and evaluating model

outputs. Tracks personal learning goals and reflects on performance improvement

opportunities. Communicates progress, risks, and needs to project leads or data

managers. Documents data sources, logic, and transformations in data

dictionaries or metadata repositories. Supports stakeholder training or

onboarding on new datasets and data services. Assists in writing user guides,

technical diagrams, and documentation for AI Orchestrations and data pipelines.

Participates in requirement gathering and feedback sessions with business users.

Supports audit and compliance documentation as needed. Provides timely responses

to questions or data requests from supported teams. Coordinates deployment of

data updates with impacted teams or systems. Performs other duties as assigned.

QUALIFICATIONS

Education, Experience and Training: Education and experience equivalent to a

Bachelor’s degree from an accredited college or university in Computer Science,

Information Systems, Data Science, AI and Analytics, or in a job-related field

of study. Master’s degree preferred. Five (5) years of work-related experience

in data engineering, data analytics, or AI/ML data processing. Certifications

(Preferred): • Certifications in cloud architecture (Azure, AWS, GCP), data

modeling, and governance tools. • Amazon Certified: AWS Data Engineer Associate

• AWS Certified Data Analytics – Specialty • Snowflake or Databricks

certification Special Requirements/Knowledge, Skills & Abilities: Must have a

valid Texas Driver's License and good driving record. Will be required to

provide a copy of 10-year driving history. Must maintain a good driving record

and remain in compliance with Article II, Subdivision II of Chapter 90 of the

Dallas County Code. “Individuals holding or considered for a position which has,

or may have, access to criminal justice databases including the FBI Criminal

Justice Information Systems, NCIC/TCIC and similar databases, must pass a

national fingerprint-based records check prior to placement in such position and

may be denied placement in such positions and/or access to such systems.

Incumbents must also maintain the ability to pass the records check while in the

position or until such time that the Commissioners Court and the County Civil

Service Commission deem this position no longer has this requirement.” •

Excellent analytical and problem-solving abilities. • Strong communication and

documentation skills. • Ability to work independently and collaboratively on

technical projects. • Strong collaboration and communication skills. • Ability

to work independently and mentor junior team members. • Knowledge of DevOps,

CI/CD, and containerized applications (Docker, Kubernetes). • Ability to design

and optimize scalable data workflows. • Knowledge of Sovereign Cloud

requirements or GovCloud environments. • Knowledge of big data frameworks

(Snowflake, Spark, Databricks, Vector Databases, Graph Databases). • Knowledge

of data warehousing, data lakes, and data modeling best practices. • Skill in

SQL, Rust, Go, Python, and/or Scala for data transformation. • Knowledge of data

privacy, compliance regulations (HIPAA, GDPR, CJIS). • Skill in implementing AI

within county/government policy frameworks. • Knowledge of Git, CI/CD pipelines,

data catalogs, Containers (Kubernetes, Docker) and business intelligence tools.

• Knowledge of cloud platforms (Azure, AWS, or GCP) and UI/UX (ReactJS/NextJS)

including data storage technologies (e.g., SQL Server, Snowflake, Parquet,

etc.). • Skill in Python, AWS Sage maker, Lang chain, Pydantic, Model Context

Protocols, Amazon Bedrock, Vector Databases, RAGs and data integration tools

(e.g., Jupiter Notebooks, API Gateways etc.). • Knowledge of streaming data

technologies (Kafka, Kinesis, Pub/Sub). Physical/Environmental

Requirements

• Occasional travel to County sites. Ability to work in a fast-paced, evolving
• technology environment.