AI Integration Engineer

We're seeking an AI Integration Engineer with a strong data engineering foundation to design and build the data infrastructure that powers our AI-driven automation and business intelligence initiatives. This role sits at the intersection of data engineering, API development, and AI, focusing on creating robust data exchange systems and multi-agent AI workflows that replace legacy processes. You'll build systems where AI agents and humans collaborate through bidirectional work delegation—both for our internal operations and the client solutions we deliver.

• Design, develop, and maintain scalable RESTful APIs for data exchange between systems
• Build real-time data pipelines and streaming architectures to support AI agent operations
• Implement API gateways, rate limiting, authentication, and security best practices
• Create comprehensive API documentation and integration guides for internal and external stakeholders
• Monitor API performance, optimize response times, and ensure high availability

• Integrate and orchestrate AI agents (LLMs, ML models, autonomous agents) into business workflows
• Design and implement agent-to-agent communication protocols and data handoffs
• Build middleware and connectors to enable AI agents to access enterprise data sources
• Develop feedback loops and monitoring systems for AI agent performance
• Create automated workflows that combine multiple AI capabilities (RAG systems, function calling, multi-agent systems)

• Maintain and optimize data warehouses, data lakes, and vector databases
• Build ETL/ELT pipelines that prepare data for AI consumption
• Implement data quality checks, validation, and governance frameworks
• Design data models that support both analytical queries and AI agent operations
• Manage structured and unstructured data storage solutions

• Collaborate with BI teams to expose data through APIs for dashboards and reporting
• Build data APIs that serve real-time metrics and KPIs
• Create data aggregation services that support analytical workloads
• Enable self-service data access through well-documented APIs and MCP servers

• Data Engineering: 3+ years of experience with modern data stack (dbt, Airflow, Spark, etc.)
• API Development:
  Strong proficiency in Python and similar languages for API development
• Database Expertise:
  Deep knowledge of SQL and No
  
  SQL databases (Postgre
  
  SQL, Mongo
  
  DB, Redis, etc.)
• Cloud Platforms:
  Experience with AWS, GCP, or Azure data and AI services
• API Technologies: REST, Graph
  
  QL, gRPC, Web Sockets, message queues (Kafka, Rabbit
  
  MQ)
• AI/ML Familiarity:
  Understanding of LLM APIs (OpenAI, Anthropic, etc.), prompt engineering, RAG systems, and vector databases (Pinecone, Weaviate, Chroma)

• Experience with AI agent frameworks (Lang Chain, Llama Index, Pydantic AI, Auto Gen, CrewAI)
• Knowledge of API management platforms (Kong, Apigee, AWS API Gateway)
• Familiarity with containerization and orchestration (Docker, Kubernetes)
• Experience with event-driven architectures and microservices
• Understanding of data security, encryption, and compliance requirements (GDPR, HIPAA, PHI, etc.)
• Background in Data Ops, MLOps, or Dev Ops practices
• Familiarity with WASM based tools and design patterns.