
Job Description
Must Have
-
3–5 years of software engineering experience, including hands-on experience building LLM or generative-AI features.
-
Production experience with RAG pipelines, embeddings, and vector databases.
-
Demonstrated ability to design, test, and refine prompts and orchestration logic for LLM-driven workflows.
-
Focus on the generative-AI application layer — distinct from classical model training and MLOps.
-
Enthusiasm for working with fast-moving generative-AI technologies.
Nice to Have
-
Exposure to OCI Generative AI services or other cloud AI platforms.
-
Familiarity with agent frameworks and tool integration.
-
Experience deploying applications to the cloud, ideally Oracle Cloud Infrastructure (OCI).
-
Awareness of responsible-AI and safety considerations.
-
Experience with vector database tuning and retrieval optimization.
-
AI or cloud certifications.
Responsibilities
-
Develop generative-AI features and applications using large language models and foundation-model APIs.
-
Implement retrieval-augmented generation (RAG) pipelines, including document processing, embeddings, and vector search.
-
Design, test, and refine prompts and orchestration logic for LLM-driven workflows.
-
Build and integrate agentic components, tool-calling, and multi-step flows.
-
Integrate AI capabilities into applications and services, including OCI Generative AI services.
-
Evaluate model outputs against quality criteria and implement guardrails and validation checks.
-
Build evaluation sets and run experiments to compare prompts, models, and configurations.
-
Collaborate with senior AI engineers and product teams to deliver working AI features.
-
Iterate on solutions based on evaluation results, performance, and user feedback.
-
Document AI components, prompts, and integration patterns for maintainability.
-
Contribute to internal reusable components and accelerators for generative-AI delivery.
Qualifications
-
Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field; equivalent experience accepted.
-
Proficiency in Python and experience with LLM frameworks (e.g., LangChain, LlamaIndex) and foundation-model APIs.
-
Working knowledge of RAG, embeddings, and vector databases.
-
Understanding of prompt engineering and orchestration techniques.
-
Ability to evaluate and improve the quality and reliability of AI outputs.
-
Solid general software-engineering skills, including version control and testing.
-
Experience integrating APIs and building application features.
© 2026 Qureos. All rights reserved.