In short
We are sharing a specialised full-time remote opportunity for an experienced AI/ML Engineer with strong expertise in Python software engineering, large language models, AI agents…
PYTHONAWSAZUREGCPLLM
📋 About the job
We are sharing a specialised full-time remote opportunity for an experienced AI/ML Engineer with strong expertise in Python software engineering, large language models, AI agents, backend API development, and cloud infrastructure to build and enhance advanced AI-powered internal platforms.
The selected professional will develop new capabilities for an AI recruiting agent, experiment with modern language models and agent frameworks, and deliver reliable, production-ready AI features. The role combines applied AI engineering with backend development, retrieval-augmented generation, agent orchestration, and continuous model evaluation to improve the accuracy, reliability, and practical effectiveness of intelligent recruiting workflows.
Key Responsibilities
LLM Application & AI Agent Development
🔹Design, develop, and enhance AI agent capabilities using modern large language models.
🔹Build intelligent workflows that support recruiting-related tasks and automated decision-support processes.
🔹Integrate LLM APIs and related AI services into internal applications.
🔹Experiment with different model configurations and implementation approaches to improve agent performance.
🔹Develop production-oriented AI features that deliver practical improvements to platform functionality.
Python Backend Engineering & API Development
🔹Build and maintain backend services using Python and modern application development frameworks.
🔹Design and implement APIs supporting AI-powered platform capabilities.
🔹Develop backend integrations connecting models, application services, and relevant data sources.
🔹Apply software engineering best practices to maintain reliability, scalability, and code quality.
🔹Collaborate with engineering teams to deliver maintainable backend infrastructure and new product features.
Prompt Engineering, RAG & Agent Orchestration
🔹Design and refine prompts, model workflows, and multi-step AI agent interactions.
🔹Develop retrieval-augmented generation (RAG) capabilities for relevant knowledge retrieval and contextual reasoning.
🔹Implement tool-calling and orchestration patterns for agent-based applications.
🔹Evaluate and improve agent workflows using frameworks such as LangChain, LangGraph, or LlamaIndex.
🔹Identify opportunities to improve model context handling, task execution, and workflow reliability.
Model Evaluation & Performance Optimisation
🔹Evaluate the quality, accuracy, and reliability of AI-generated outputs.