Artificial Intelligence Engineer

Pyramid Consulting, Inc; Greater London; On-site; GBP 90,000 - 120,000; Full time

Job summary

Pyramid Consulting, Inc. is seeking an AI Engineer to design, build, and optimize AI-powered services for real‑world HR technology use cases.

The role is hands‑on, focused on secure, scalable, and measurable AI delivery within a cloud environment. The candidate will specialize in integrating LLMs with Azure OpenAI, applying RAG patterns, prompt and context pipelines, and evaluating model performance to improve relevance, fairness, and explainability.

Qualifications

• Strong Python development experience.
• Experience in AI application development with cloud model integration.
• Proficiency with LangChain, LangGraph and Pydantic.
• Ability to implement RAG patterns and Agentic RAG in Azure environments.
• Understanding GPT token usage, latency analytics, and budget guardrails.
• Knowledge of AI guardrails, prompt fuzzing, adversarial and bias testing.
• Experience with embeddings, vector databases, and real‑time data integration.
• Hands‑on Azure OpenAI and Azure Cognitive/Search usage.
• Commitment to quality, maintainability, and documentation.

Responsibilities

• Design and build AI-powered services for enterprise HR tech use cases.
• Integrate and optimize LLMs and intelligent systems in Azure.
• Apply RAG, MCP, Function Calling and A2A patterns to practical solutions.
• Develop pipelines for prompt design, context handling, embeddings, and chunking.
• Evaluate model output and optimize application performance for quality and fairness.
• Implement guardrails, prompt testing, and bias testing in production workflows.
• Deliver cloud-based AI applications at scale using Azure AI services.
• Ensure security, reliability, observability, and thorough documentation.

Skills

Python development

AI application development

LangChain/LangGraph

Pydantic

Azure OpenAI

LLM integration

RAG patterns

Prompt engineering

Embeddings/vector databases

Quality and maintainability

Job description

We are looking for an AI Engineer to design, build, integrate, and optimize AI-powered services and intelligent systems that enhance employee experience and support real-world HR technology use cases. The role is hands‑on and engineering‑focused, with emphasis on secure, scalable, measurable, and maintainable AI application delivery.

Primary focus - AI services, LLM integration, RAG patterns, prompt/context pipelines, evaluation, and Azure AI services

Key responsibilities

• Design and develop AI-powered services that enhance employee experience and support HR technology use cases.
• Integrate and optimize large language models and intelligent systems using Azure OpenAI and other cloud‑native AI tools.
• Apply advanced AI architecture patterns such as Retrieval‑Augmented Generation (RAG), Agentic RAG, MCP, Function Calling, and A2A to practical enterprise use cases.
• Engineer robust pipelines for prompt design, context handling, embeddings, chunking strategies, and real‑time data integration.
• Evaluate, test, and optimize model output and application performance to improve relevance, robustness, fairness, and explainability.
• Implement guardrails, prompt testing, adversarial and bias testing, and other controls needed for responsible AI application delivery.
• Develop and deploy cloud‑based AI applications at scale using Azure Cloud Services for AI, including Azure OpenAI and Azure AI Search.
• Ensure solutions are secure, reliable, observable, maintainable, and well documented.

Required skills and experience

• Excellent Python skills and hands‑on experience
• Experience in AI application development, with focus on cloud‑based AI model integration, deployment, and optimization.
• Experience with AI/ML and agentic application frameworks such as LangChain, LangGraph, Pydantic
• Proficiency in advanced AI architecture patterns, including RAG, Agentic RAG, MCP, Function Calling, and A2A, especially in an Azure environment
• Good understanding of GPT token usage, latency analytics, and budget guardrails.
• Sound understanding of AI guardrails, prompt fuzzing, adversarial testing, and bias testing.
• Experience in prompt engineering, context engineering, vector databases, embedding and chunking strategies, and real‑time data integration.
• Experience evaluating model output and optimizing AI application performance.
• Hands‑on experience with Azure Cloud Services for AI, including Azure OpenAI and Azure AI Search.
• Strong commitment to quality, maintainability, documentation, and continuous learning.

Nice to have

• Understanding of alignment and feedback techniques, synthetic data generation, and continuous human‑in‑the‑loop review loops.
• Experience designing evaluation approaches for relevance, groundedness, explainability, safety, robustness, and operational quality.
• Experience packaging AI features for production use with logging, monitoring, observability, and controlled rollout patterns.

Profile we are looking for

• A pragmatic, hands‑on AI engineer who can build production‑grade AI services, integrate LLM capabilities into enterprise applications, and engineer reliable prompt, retrieval, context, evaluation, and deployment pipelines. The ideal candidate is technically strong, delivery-oriented, quality‑minded, and comfortable working on secure and scalable AI applications in a cloud environment.