Software Developer – AI & Agentic Applications

About the role

We are seeking a skilled AI Engineer to design, develop, and deploy AI‑powered applications that leverage Large Language Models (LLMs) and agentic AI frameworks. The role focuses on building production‑grade Retrieval‑Augmented Generation (RAG) pipelines, multi‑step AI agents, and scalable backend services.

Key responsibilities

• Design, develop, and launch AI applications using LLMs and agentic AI frameworks.
• Build and optimise RAG systems for semantic search and knowledge retrieval.
• Create multi‑step AI agent workflows and reasoning pipelines.
• Integrate LLM APIs such as OpenAI, Anthropic, and Google AI.
• Work with vector databases and embedding models for efficient retrieval.
• Develop prompt‑engineering strategies to ensure reliable outputs.
• Implement REST APIs and backend services using FastAPI, Flask, or Django.
• Collaborate with product and engineering teams to embed AI capabilities into existing platforms.
• Monitor model performance, evaluate response quality, and continuously improve deployments.

Required profile

• 2+ years of experience developing AI/LLM applications.
• Hands‑on experience deploying AI agents in live production environments.
• Familiarity with Docker, cloud platforms, CI/CD pipelines, and AI monitoring tools.
• Strong problem‑solving, analytical, and communication skills.
• Ability to work independently in a remote setting and a passion for generative AI.

Required skills

• Python
• Large Language Models (LLMs)
• Agentic AI systems
• RAG pipelines
• Prompt engineering
• Vector databases
• LangChain, LlamaIndex, AutoGen
• OpenAI, Anthropic, Google AI APIs
• FastAPI, Flask, Django
• API integrations
• AI workflow orchestration
• TensorFlow, PyTorch
• Docker
• Cloud platforms
• CI/CD pipelines
• AI monitoring tools