Job Description
The Senior AI Application Engineer will play a key role within the OAL engineering organization, designing and operating high-performance, cloud-native application services on Kubernetes to power advanced AI agents, RAG pipelines, large-scale distributed data workloads, and intelligent automation capabilities.
In this role, you will engineer low-latency microservices integrating LLMs, agentic orchestration frameworks, and AI runtime components while rapidly prototyping and hardening production-grade capabilities to enable innovative AI-driven solutions on Oracle Cloud Infrastructure.
Technical Expertise:
- Bachelor’s or Master’s degree in Computer Science, Engineering, or related technical field. Minimum 3+ years’ hands-on experience in software development using Java, Python, Spring Boot, with strong grounding in data structures, algorithms, and their application in solving complex engineering challenges.
- Experience in designing, scalable microservices in an enterprise environment.
- Proven ability to rapidly learn new technologies, prototype solutions, and independently design and implement application components.
- Practical exposure to working with Large Language Models (OpenAI, Grok, or open-source variants), including prompt engineering practices, fine-tuning methods, and model deployment strategies.
- Hands-on development of agent-based workflows using frameworks such as OpenAI Agent SDK, LangGraph, or equivalent agent orchestration toolsets.
- Experience implementing Retrieval-Augmented Generation components including indexing, metadata strategies, hybrid search, relevance evaluation, and pipeline integration.
- Experience with Oracle Cloud Infrastructure, including services such as OCI GenAI Service, Object Storage, API Gateway, Functions, or Streaming.
- Hands-on familiarity with Kubernetes on Oracle Kubernetes Engine (OKE) and container tooling such as Podman or Docker.
- Familiarity with vector-enabled data systems such as Oracle 23ai Vector Database, Pinecone, FAISS, or comparable technologies (desirable).
Soft Skills & Leadership
- Proven ability to drive technical outcomes, take ownership of deliverables, and work independently in fast-evolving AI solution spaces.
- Strong communication skills, with the ability to articulate technical concepts, document solution approaches, and collaborate across distributed teams.
- Demonstrated problem-solving ability when working with complex AI workloads, distributed systems, and cloud-native application behaviours.
- A proactive, experimentation-oriented mindset with a strong willingness to learn emerging AI technologies, frameworks, and engineering patterns.
Key Responsibilities
Cloud Application Development
- Design and develop cloud-native application services on Kubernetes using Java, Python, and Spring Boot.
- Integrate application components with OCI services, including GenAI Service, Object Storage, and API Gateway.
AI, LLMs, and Agentic Systems
- Implement AI-powered capabilities using LLMs, prompt engineering, and agentic frameworks such as OpenAI Agent SDK or LangGraph.
- Build RAG workflows including embeddings, indexing, and hybrid search.
DevOps and Deployment
- Support CI/CD processes and containerized deployment workflows using Podman, Docker, and OKE.
- Troubleshoot application and runtime issues across distributed environments.
Collaboration and Knowledge Sharing
- Work with cross-functional engineering teams to align solution designs with business requirements.
- Conduct independent research on emerging AI technologies, tools, and engineering patterns to introduce improvements and new solution approaches.
- Share knowledge, mentor peers, and contribute to internal enablement of AI and cloud development best practices.
