AI Engineer

•Design and develop production-ready Generative AI applications using Python, LLMs and modern AI technologies.

•Build Retrieval-Augmented Generation (RAG) pipelines for document understanding, enterprise knowledge retrieval and context-aware responses.

•Develop Agentic AI workflows using tool calling, function calling, structured outputs and multi-step reasoning.

•Build and maintain backend AI services and REST APIs using Python and frameworks such as FastAPI or Flask.

•Integrate LLM platforms including OpenAI, Hugging Face and other hosted or local AI models.

•Work with embeddings and vector databases such as pgvector, FAISS, ChromaDB or similar technologies.

•Develop conversational AI and Voice AI solutions using Speech-to-Text, Text-to-Speech and real-time audio technologies.

•Integrate AI capabilities with web, mobile and enterprise applications.

•Design AI workflows capable of interpreting user commands and securely interacting with application functions and external tools.

•Implement prompt engineering, context management, structured prompting and model-response validation.

•Improve AI response quality, retrieval accuracy, latency, reliability and overall application performance.

•Evaluate model outputs and implement techniques to reduce hallucinations and improve answer relevance.

•Implement chunking, metadata filtering, retrieval, reranking and other RAG optimisation techniques.

•Work with relational, NoSQL and vector databases as required by the application.

•Containerize and deploy AI services using Docker and modern deployment environments.

•Debug issues across AI models, APIs, databases, integrations and production services.

•Participate in architecture discussions, code reviews, testing and technical documentation.

•Research and evaluate emerging LLM, Agentic AI, Voice AI and Generative AI technologies.

•Collaborate with frontend, backend, QA and product teams to deliver complete AI-powered products.