[Hiring] Generative AI Application Engineer @Artech

Role Description

The Generative AI Application Engineer builds and integrates AI‐enabled capabilities into enterprise applications as part of the modernization program. This role focuses on applied AI development—prompt engineering, retrieval‐augmented generation (RAG), vector search integration, and LLM orchestration—rather than research model development. The engineer works under the direction of a Senior GenAI Lead and collaborates closely with APEX developers, data integration teams, DevOps, and QA to deliver secure, reliable, production‐ready AI features.

Key Responsibilities

• Applied GenAI Development
  • Implement components of RAG pipelines, including embeddings, vector search, and hybrid retrieval logic.
  • Develop prompt templates, grounding strategies, guardrails, and LLM orchestration flows based on patterns defined by the GenAI Lead.
  • Integrate GenAI services with enterprise applications (e.g., Oracle APEX) through REST APIs, backend microservices, or PL/SQL callouts.
  • Implement guardrails, validation logic, fallback behaviors, and secure error‐handling for AI‐driven workflows.
• Integration & Data Enablement
  • Integrate applications with vector databases or vector search functionality (Oracle Database preferred).
  • Collaborate with data engineering teams to source structured data, understand schemas, and define access patterns for AI workloads.
  • Create and maintain evaluation datasets; support retrieval quality metrics and prompt regression testing.
• DevOps, Testing & Governance
  • Work with DevOps and cloud engineering teams on deployment pipelines, secrets management, configuration, and monitoring for AI services.
  • Support QA engineers in developing automated tests for GenAI‐enabled functionality.
  • Ensure AI components meet enterprise requirements for security, auditing, logging, and cost governance.
• Collaboration & Delivery
  • Participate in Agile delivery processes, including sprint planning, demos, and refinement.
  • Partner with application developers, architects, QA testers, and business analysts to deliver cohesive end‐to‐end features.
  • Contribute to documentation, design patterns, and runbooks to support long‐term operational readiness.

Qualifications

• 2–5 years of software engineering experience in application or backend development.
• Hands‐on experience building applied GenAI solutions (RAG, prompt engineering, LLM orchestration).
• Experience using LLM APIs (e.g., OCI Generative AI, OpenAI, Azure OpenAI, Anthropic).
• Proficiency with Python or Node.js for backend and integration development.
• Familiarity with structured data, SQL, and working with relational databases.
• Experience integrating with vector databases or vector search functionality (Oracle Database preferred).
• Understanding of evaluation methods such as retrieval precision/recall, grounding accuracy, or automated prompt testing.
• Ability to work effectively with cross‐functional teams (APEX developers, Data Engineers, DevOps, QA).
• Strong communication and documentation skills.

Preferred Qualifications

• Experience with Oracle Cloud Infrastructure (OCI), Oracle APEX, or Autonomous Database.
• Hands‐on experience with vector search in Oracle Database 23c or Autonomous Database.
• Familiarity with enterprise security practices, API gateways, and secrets management.
• Exposure to guardrail frameworks, grounding techniques, or advanced RAG patterns.
• Experience building user‐facing AI features within enterprise environments.