OTAKOYI is looking for a smart and eager Senior AI Engineer to join our project team and contribute to the development of an advanced enterprise-grade AI platform.
Our partner is building a powerful agentic AI system designed to centralize knowledge, automate workflows, and enhance productivity across the organization. This platform goes beyond traditional chat solutions — it serves as an AI-driven layer supporting intelligent task orchestration and data interaction.
We are seeking an engineer who enjoys building production-ready AI systems, solving complex technical challenges, and contributing to architectural decisions while staying deeply involved in implementation.
What You’ll Do
- AI Development & Implementation (Core Focus)
- Design and implement LLM-based applications and RAG pipelines
- Develop scalable backend services using Python and FastAPI
- Integrate vector databases (e.g., Milvus), relational and non-relational databases (PostgreSQL, CosmosDB)
- Build and optimize generative AI pipelines from experimentation to production. Transit proof-of-concepts into stable, maintainable production systems
Cloud & Infrastructure
- Work with Azure-based cloud environments (or similar cloud platforms)
- Deploy and manage containerized workloads using Docker, argo-wrkflows, Kubernetes and Rancher
- Ensure scalability, performance, and reliability of AI services
Architectural Contribution
- Contribute to architecture decisions and system design discussions
- Propose improvements to AI workflows, infrastructure, and model performance
- Maintain high standards of code quality, testing, and documentation
- Clearly communicate technical trade-offs within cross-functional teams
Required Skills
- Hands-on experience building applications with LLM APIs (OpenAI, Azure OpenAI, Anthropic, etc.)
- Experience implementing RAG pipelines with embedding and retrieval optimization
- Practical knowledge of prompt engineering, tool/function calling, and structured outputs
- Experience building agentic or multi-step LLM workflows (LangChain, LlamaIndex, or similar)
- Understanding of LLM performance evaluation, guardrails, and hallucination mitigation
- Experience with LLM observability and monitoring tools
- Experience working with vector databases (Milvus, Azure AI Search or similar)
- Backend development experience (FastAPI or similar async frameworks)
- Understanding of API design and integration
- Experience with Docker and Kubernetes
- Strong problem-solving skills and attention to detail
- Upper-Intermediate English or higher
Nice to Have
- Experience with multi-modal AI systems
- Experience with Model Context Protocol (MCP) or similar LLM-to-tool integration standards
- Familiarity with Microsoft ecosystem integrations (e.g., MS Graph, Copilot tools)
- Experience with CI/CD pipelines and DevOps practices
- Experience working in agile development environments
What We Offer
- Opportunity to build and scale a production-grade AI platform
- Direct impact on the evolution of enterprise AI solutions
- Collaboration within a cross-functional, innovation-driven team
- A challenging environment focused on growth and technical excellence
