Senior AI Engineer (Gen AI & RAG)

The Portfolio Group; Greater London; On-site; GBP 110,000 - 140,000; Full time

Job summary

The Portfolio Group seeks a Senior AI Engineer to lead the design and delivery of production-grade generative AI capabilities. You will architect RAG pipelines, graph-based retrieval, and agentic workflows to create measurable business value for clients.

You will mentor engineers, drive rigorous evaluation, and partner with Product and Platform teams to move AI experimentation into scalable production.

Qualifications

• Strong Python proficiency for production-grade AI development.
• Experience building Retrieval-Augmented Generation (RAG) systems.
• Hands-on experience with model adaptation techniques (prompting, fine-tuning, distillation).
• Strong grounding in evaluation and experimentation for generative AI.
• Experience delivering complex AI/ML systems in live production.

Responsibilities

• Design, build, and deploy production-grade generative AI systems at scale.
• Develop and improve RAG pipelines leveraging proprietary content.
• Provide technical leadership and guidance across the team.

Skills

Python

RAG systems

Production AI

Tools

LlamaIndex

LangChain

LangGraph

Job description

Join an award-winning, internationally recognised B2B Consultancy as a Senior AI Engineer, where you will play a central role in delivering and evolving production-grade generative AI capabilities that power real-world business outcomes.

This is a senior, hands‑on engineering role focused on building the intelligence layer of next-generation AI products. You will architect and implement Retrieval-Augmented Generation (RAG) pipelines, agentic workflows, and rigorous evaluation frameworks that ensure AI systems are accurate, reliable, and grounded in genuine business value.

Reporting to the Director of AI, you will bridge strategy and execution - translating architectural direction into high-quality, scalable implementations in close collaboration with AI Platform Engineering.

What You'll Do

• Design, build, and deploy production‑grade generative AI systems that perform reliably at scale.
• Implement and continuously improve RAG pipelines that effectively leverage proprietary and domain‑specific content.
• Develop agentic and workflow‑driven AI patterns with a strong emphasis on determinism, quality, and long‑term maintainability.
• Apply model adaptation techniques - prompting, fine‑tuning, distillation - to optimise for quality, latency, and cost efficiency.
• Drive strong experimentation and evaluation practices, measuring correctness, faithfulness, and robustness across AI outputs.
• Provide hands‑on technical leadership, mentoring engineers and contributing meaningful code‑level guidance across the team.
• Work closely with platform, product, and delivery teams to accelerate the path from AI experimentation to production deployment.
• Explore and apply advanced retrieval approaches, including Graph‑RAG and structured knowledge representation, where they deliver clear value.

Required Skills & Experience

• Strong Python proficiency for production‑grade AI development, with hands‑on experience across LlamaIndex, LangChain, and LangGraph.
• Proven track record building Retrieval‑Augmented Generation (RAG) systems; Graph‑RAG exposure is a distinct advantage.
• Practical experience with model adaptation techniques including prompting, fine‑tuning, instruction tuning, or knowledge distillation.
• Solid grounding in evaluation and experimentation methodology for generative AI, with a focus on correctness, faithfulness, and robustness.
• Demonstrable experience owning the technical design and delivery of complex AI, ML, or data‑driven systems in live production environments.
• A background operating at senior engineer or technical lead level – comfortable balancing rapid experimentation with disciplined production delivery, and communicating with clarity across technical and non‑technical stakeholders.

This is a compelling opportunity to work at the forefront of applied Generative AI, where your contributions directly shape customer‑facing products and drive measurable business impact. You will bring genuine technical ownership and autonomy, supported by a world‑class leadership team with a clear and ambitious AI roadmap.