AI Data Engineer (15+ Years)

Canvendor is a company that specializes in AI solutions, and they are seeking an experienced AI Data Engineer. The role involves developing and implementing AI systems and microservices, as well as integrating them with various APIs and data sources.

Responsibilities:

• Proven experience as a software engineer with strong proficiency in Python and/or Java, writing clean, scalable, production-grade code
• Solid experience designing and building microservices and RESTful APIs in distributed, cloud-based environments
• Experience designing, implementing, and extending AI agentic systems, including tool use, planning, and autonomous decision-making workflows
• Experience building multi-agent systems where multiple agents collaborate, delegate, and coordinate to complete complex tasks
• Hands-on experience building conversational or chat systems with both short-term (session) and long-term (persistent) context management
• Experience building Retrieval-Augmented Generation (RAG) systems – including document ingestion, chunking strategies, vector stores, and retrieval pipelines
• Experience building MCP servers
• Experience integrating agentic systems with external APIs, third-party services, and enterprise data sources
• Strong understanding of security in agentic systems – authentication, authorization, least-privilege access, prompt injection defense, and audit logging
• Knowledge of relational databases (e.g. PostgreSQL, Microsoft SQL Server) and vector databases (e.g. Qdrant, Pinecone, pgvector, Weaviate)
• Experience using system and performance monitoring tools (e.g. New Relic, Datadog)
• Proficient in Git and comfortable working in CI/CD-driven development workflows
• Excellent critical-thinking, communication, and personal leadership skills
• Self-starter with the ability to deliver with minimal supervision

Requirements:

• Proven experience as a software engineer with strong proficiency in Python and/or Java, writing clean, scalable, production-grade code
• Solid experience designing and building microservices and RESTful APIs in distributed, cloud-based environments
• Experience designing, implementing, and extending AI agentic systems, including tool use, planning, and autonomous decision-making workflows
• Experience building multi-agent systems where multiple agents collaborate, delegate, and coordinate to complete complex tasks
• Hands-on experience building conversational or chat systems with both short-term (session) and long-term (persistent) context management
• Experience building Retrieval-Augmented Generation (RAG) systems – including document ingestion, chunking strategies, vector stores, and retrieval pipelines
• Experience building MCP servers
• Experience integrating agentic systems with external APIs, third-party services, and enterprise data sources
• Strong understanding of security in agentic systems – authentication, authorization, least-privilege access, prompt injection defense, and audit logging
• Knowledge of relational databases (e.g. PostgreSQL, Microsoft SQL Server) and vector databases (e.g. Qdrant, Pinecone, pgvector, Weaviate)
• Experience using system and performance monitoring tools (e.g. New Relic, Datadog)
• Proficient in Git and comfortable working in CI/CD-driven development workflows
• Excellent critical-thinking, communication, and personal leadership skills
• Self-starter with the ability to deliver with minimal supervision
• BSc/BA in Computer Science or a related degree
• Experience with distributed computing
• Experience writing code/scripts in Python
• Experience with Spring Boot
• Nice to have: React, Selenium automation and cloud experience
• Nice to have: document parsing systems, including extraction from PDFs, structured/unstructured data sources, and handling diverse file formats
• Experience with Docker, Kubernetes and Istio
• Experience with Ansible
• Experience with CI/CD pipelines using Spinnaker and/or GitHub Actions
• Linux and IP networking knowledge
• Experience with AWS/Azure cloud services or equivalent
• Experience with Terraform for infrastructure as code and cloud provisioning
• Nice to have: Experience with SAML, OAuth and OpenID Connect
• Experience working on a SaaS product
• Experience with Service Oriented Architecture
• On-call experience with production grade systems
• Has mentored others in a professional setting
• Generative AI Code Assistants – Use of Generative AI Code Assistants (e.g. GitHub Copilot) and knowledge of latest Generative AI model capabilities