What are the responsibilities and job description for the Senior Full Stack GenAI Engineer position at Jobs via Dice?
Dice is the leading career destination for tech experts at every stage of their careers. Our client, Interon IT Solutions LLC, is seeking the following. Apply via Dice today!
#W2 only
Job title: Senior Full Stack GenAI Engineer
Location: Reston VA - In person interviews so need Local In EAST coast only
Description:
Senior Full Stack GenAI Engineer with 10 years of experience to design and build agentic AI
solutions that automate enterprise workloads and business processes.
The ideal candidate will have strong expertise in Python-based backend development, LLM-
powered applications, cloud-native deployment, vector databases, and modern DevOps practices.
This role involves building end-to-end AI systems that integrate with enterprise platforms,
automate workflows, and deliver production-grade AI applications.
Key Responsibilities
Design and develop agentic AI applications that automate enterprise workflows and decision-
making processes.
Build scalable backend services using Python, FastAPI, and Pydantic.
Develop and deploy LLM-powered applications using models such as GPT and Claude.
Build AI agents and orchestration workflows using LangChain or Strands.
Implement Retrieval Augmented Generation (RAG) solutions using vector databases (pgvector,
Pinecone, Weaviate).
Perform data analysis, preparation, and curation to build high-quality datasets for AI and
knowledge retrieval systems.
Design and implement document ingestion pipelines for enterprise knowledge sources such as
SharePoint, Confluence, and Jira.
Deploy AI workloads on AWS (Bedrock, ECS Fargate, S3) with proper security and scalability
practices.
Develop and integrate enterprise APIs using REST, GraphQL, WebSockets, and web services.
Implement secure authentication and authorization using Ping Identity, OAuth2, OIDC, and
SSO.
Build user interfaces for AI applications using ReactJS or Streamlit.
DevOps & Deployment
Build and manage CI/CD pipelines using Jenkins or GitLab.
Implement GitOps practices for automated deployments.
Containerize applications using Docker and deploy to cloud platforms.
Implement security best practices, vulnerability scanning, dependency management, and
container security.
Required Skills
Backend & APIs
Python
FastAPI
Pydantic
REST APIs, GraphQL, WebSockets
GenAI & Agent Frameworks
LLMs (GPT, Claude)
LangChain or Strands
Retrieval Augmented Generation (RAG)
NLP (Natural Language Processing)
Data & AI Pipelines
Data analysis, data preparation, and data curation
Document ingestion and knowledge base creation
Embeddings and semantic search
Vector Databases
pgvector
Pinecone
Weaviate
Cloud & Platforms
AWS (Bedrock, ECS Fargate, S3, Guardrails)
Databases
PostgreSQL
DynamoDB
Security & Identity
Ping Identity
OAuth2 / OIDC
SSO, Authentication & Authorization
DevOps
Jenkins
GitLab
GitOps practices
Docker containerization
Security vulnerability mitigation
Frontend
ReactJS
Streamlit
Enterprise Tools
Portkey (AI Gateway)
Apigee (API Gateway)
Jira, Confluence, SharePoint
#W2 only
Job title: Senior Full Stack GenAI Engineer
Location: Reston VA - In person interviews so need Local In EAST coast only
Description:
Senior Full Stack GenAI Engineer with 10 years of experience to design and build agentic AI
solutions that automate enterprise workloads and business processes.
The ideal candidate will have strong expertise in Python-based backend development, LLM-
powered applications, cloud-native deployment, vector databases, and modern DevOps practices.
This role involves building end-to-end AI systems that integrate with enterprise platforms,
automate workflows, and deliver production-grade AI applications.
Key Responsibilities
Design and develop agentic AI applications that automate enterprise workflows and decision-
making processes.
Build scalable backend services using Python, FastAPI, and Pydantic.
Develop and deploy LLM-powered applications using models such as GPT and Claude.
Build AI agents and orchestration workflows using LangChain or Strands.
Implement Retrieval Augmented Generation (RAG) solutions using vector databases (pgvector,
Pinecone, Weaviate).
Perform data analysis, preparation, and curation to build high-quality datasets for AI and
knowledge retrieval systems.
Design and implement document ingestion pipelines for enterprise knowledge sources such as
SharePoint, Confluence, and Jira.
Deploy AI workloads on AWS (Bedrock, ECS Fargate, S3) with proper security and scalability
practices.
Develop and integrate enterprise APIs using REST, GraphQL, WebSockets, and web services.
Implement secure authentication and authorization using Ping Identity, OAuth2, OIDC, and
SSO.
Build user interfaces for AI applications using ReactJS or Streamlit.
DevOps & Deployment
Build and manage CI/CD pipelines using Jenkins or GitLab.
Implement GitOps practices for automated deployments.
Containerize applications using Docker and deploy to cloud platforms.
Implement security best practices, vulnerability scanning, dependency management, and
container security.
Required Skills
Backend & APIs
Python
FastAPI
Pydantic
REST APIs, GraphQL, WebSockets
GenAI & Agent Frameworks
LLMs (GPT, Claude)
LangChain or Strands
Retrieval Augmented Generation (RAG)
NLP (Natural Language Processing)
Data & AI Pipelines
Data analysis, data preparation, and data curation
Document ingestion and knowledge base creation
Embeddings and semantic search
Vector Databases
pgvector
Pinecone
Weaviate
Cloud & Platforms
AWS (Bedrock, ECS Fargate, S3, Guardrails)
Databases
PostgreSQL
DynamoDB
Security & Identity
Ping Identity
OAuth2 / OIDC
SSO, Authentication & Authorization
DevOps
Jenkins
GitLab
GitOps practices
Docker containerization
Security vulnerability mitigation
Frontend
ReactJS
Streamlit
Enterprise Tools
Portkey (AI Gateway)
Apigee (API Gateway)
Jira, Confluence, SharePoint