Traineeship

AI Product and Research Engineer

KEY SKILLS: SQL, MLOps & Deployment: Implement CI/CD pipelines, GitLab Actions, Apache Airflow, AI-assisted document review, prompt engineering, Python, OpenAI, HuggingFace

4.7 (253 user ratings)

Rated 4.7 out of 5

What You’ll Learn:

You’ll learn database systems PostgreSQL, MongoDB and caching layers (Redis); Open-source contributions or published AI demos; Understanding of cost-optimisation, monitoring for LLM usage and model-API trade-offs. Familiarity with prompt engineering best practices and “vibe-coding” tools (e.g., GitHub Copilot, Cursor IDE), Pinecone, FAISS, Weaviate)

At the end of this course, you will know how to;

Turn wild LLM ideas into working demos overnight, build automation, ship Python or TypeScript prototypes, Craft, iterate, and optimize prompts for APIs (OpenAI, Cohere, Anthropic). Build multi-step “chains” using LangChain, LlamaIndex, or custom controllers. Develop and maintain AI microservices using Docker, Kubernetes, and FastAPI, ensuring smooth model serving and error handling. Vector Search & Retrieval: Implement retrieval-augmented workflows: ingest documents, index embeddings (Pinecone, FAISS, Weaviate). Build similarity search features. Create interactive AI demos and proofs-of-concept with Streamlit, Gradio, or Next.js for stakeholder feedback. Cross-Functional Collaboration: Participate in code reviews, architectural discussions, and sprint planning to deliver features end-to-end.