AI Agentic Systems Engineer & Data Engineer (2 Positions)

Job Title : Data Engineers

Type : Onsite (Hybrid 3 to 4 days to office)

Interview : In Person

Locations : McLean VA, Richmond VA, Dallas TX

NO OPT / CPT

Job Description :

A Data Engineer with Python, PySpark, and AWS expertise is responsible for designing, building, and maintaining scalable and efficient data pipelines in cloud environment

Responsibilities :

Design, develop, and maintain robust ETL / ELT pipelines using Python and PySpark for data ingestion, transformation, and processing.

Work extensively with AWS cloud services such such as S3, Glue, EMR, Lambda, Redshift, Athena, and DynamoDB for data storage, processing, and warehousing.

Build and optimize data ingestion and processing frameworks for large-scale data sets, ensuring data quality, consistency, and accuracy.

Collaborate with data architects, data scientists, and business intelligence teams to understand data requirements and deliver effective data solutions.

Implement data governance, lineage, and security best practices within data pipelines and infrastructure.

Automate data workflows and improve data pipeline performance through optimization and tuning.

Develop and maintain documentation for data solutions, including data dictionaries, lineage, and technical specifications.

Participate in code reviews, contribute to continuous improvement initiatives, and troubleshoot complex data and pipeline issues

Required Skills :

Strong programming proficiency in Python, including libraries like Pandas and extensive experience with PySpark for distributed data processing.

Solid understanding and practical experience with Apache Spark / PySpark for large-scale data transformations.

Demonstrated experience with AWS data services, including S3, Glue, EMR, Lambda, Redshift, and Athena.

Proficiency in SQL and a strong understanding of data modeling, schema design, and data warehousing concepts.

Experience with workflow orchestration tools such as Apache Airflow or AWS Step Functions.

Familiarity with CI / CD pipelines and version control systems (e.g., Git).

Excellent problem-solving, analytical, and communication skills, with the ability to work effectively in a team environment.

Preferred Skills :

Experience with streaming frameworks like Kafka or Kinesis.

Knowledge of other data warehousing solutions like Snowflake

Job Title : AI Agentic Systems Engineer (LangChain / LangGraph / Google APIs)

Locations : Dallas TX, Cary NC, Raleigh NC

Type : Onsite (Hybrid 3 days to office)

Interview Mode : In Person

Job Description : AI Agentic Systems Engineer

A job description for a role involving LangChain, LangGraph, and Google APIs typically involves creating advanced AI agents and systems. This position, often titled AI / ML Engineer or Agentic Systems Developer, includes designing and implementing complex workflows that use large language models (LLMs) like Google's Gemini and integrate with external tools via Google APIs.

Summary :

This position focuses on developing, deploying, and maintaining advanced AI agents and multi-agent systems. The requirements include experience with LangChain, especially LangGraph for orchestrating stateful agents, and integrating with Google's generative AI models and other cloud APIs

Key Responsibilities :

Design and build robust agentic systems for complex tasks and interactions.

Use the LangChain framework to integrate LLMs, tools, and memory.

Use LangGraph to model and orchestrate agents as stateful graphs.

Integrate Google's Generative AI models (e.g., Gemini) using relevant LangChain packages.

Implement tool-calling features for agents to interact with external Google APIs (e.g., Search, Calendar, Cloud services).

Develop and maintain prototypes and production-ready systems.

Collaborate with cross-functional teams.

Apply best practices in AI system development, including monitoring and observability using tools like LangSmith.

Qualifications :

Experience in AI / ML engineering, with a focus on agentic AI or autonomous systems development.

Proficiency in Python and the LangChain ecosystem, including LangGraph.

Experience with Google Generative AI models (Gemini) and the langchain-google-genai package.

Experience using Google APIs (e.g., Google Search API, Google Calendar API) for custom tools.