Generative AI Engineer

About the role

The company is looking for a hands-on AI Engineer with at least 1 year of experience to build, develop and integrate AI-powered applications using Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) and Agentic AI frameworks. The focus is on applied AI engineering: building real-world AI solutions, integrating intelligent capabilities into applications and improving the reliability, scalability and performance of AI systems.

Key responsibilities

• Develop Python-based applications using LLMs and Generative AI, and build AI solutions with LangChain and LangGraph.
• Integrate OpenAI, Anthropic Claude, Gemini and other LLM APIs, and design RAG pipelines covering document processing, chunking, embeddings and semantic search.
• Integrate vector databases such as Chroma, FAISS, Pinecone or pgvector, and optimise retrieval relevance, accuracy and response quality.
• Build AI agents with tool calling, API integration and multi-step task execution, using LangGraph for stateful workflows and orchestration.
• Implement prompt engineering, context management and agent memory, and integrate agents with external APIs, databases and business applications.
• Design REST APIs with Python and FastAPI, write clean, reusable code, and debug and optimise backend and AI applications.
• Evaluate LLM responses for accuracy and relevance, minimise hallucinations, and optimise latency, token consumption and API costs.
• Implement logging, retries, error handling and monitoring, and collaborate with the team to improve performance and reliability.

Required profile

• Minimum 1 year of software development experience, preferably in Python and AI/LLM applications.
• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science or a related field; candidates with strong practical experience and relevant projects are also encouraged to apply.

Required skills

• Python, OOP, asynchronous programming basics and API integration.
• LangChain, LangGraph and LLM workflows; RAG and vector search.
• FastAPI or Flask, REST APIs, SQL, Git and debugging.
• Good to have: AWS (Lambda, S3, API Gateway, Bedrock, EC2), Docker, CI/CD, Model Context Protocol, multi-agent systems, LLM evaluation and observability, hybrid search and reranking, prompt optimisation and caching.