AI/ML Engineer: RAG Pipelines & LLM-Powered Insights

Nexalytica Ltd.; Greater London; Hybrid; GBP 90,000 - 120,000; Full time

Benefits offered by this job

Annual learning budget £2,500

Hybrid work from London office

Latest hardware and tooling

25 days annual leave + bank holidays

Private medical insurance and pension

Job summary

Nexalytica Ltd. in London, UK, is seeking an AI/ML Engineer to design and improve the core intelligence layer for our conversational analytics platform. You will help the system understand user questions, generate SQL, and deliver insights from complex datasets.

You will build RAG pipelines, craft prompts, and implement evaluation frameworks to scale quality. This role collaborates with product designers and full‑stack engineers to ship customer‑facing features.

Qualifications

• 3–5 years of experience building ML/NLP systems in production.
• Strong proficiency in Python and ML frameworks like PyTorch or TensorFlow.
• Hands-on experience with large language models, prompt engineering, and RAG pipelines.
• Familiarity with vector databases (Pinecone, Weaviate, Qdrant, or similar).
• Solid understanding of SQL and relational databases.
• Experience building evaluation and testing frameworks for AI systems.

Responsibilities

• Design and improve the core intelligence layer powering the conversational analytics platform.
• Build and refine retrieval-augmented generation (RAG) pipelines and prompt strategies.
• Develop evaluation frameworks, anomaly detection models, and predictive analytics features.
• Collaborate with product designers and full-stack engineers to ship features used by customers.

Skills

Python

NLP

RAG architectures

Vector databases

SQL

PyTorch/Transformers

Education

Bachelor's or Master's Degree in Computer Science, Machine Learning, or related field

Tools

PyTorch

TensorFlow

Pinecone

Weaviate

Qdrant

Job description

Nexalytica Ltd. in London, UK, is seeking an AI/ML Engineer to design and improve the core intelligence layer for our conversational analytics platform. You will help the system understand user questions, generate SQL, and deliver insights from complex datasets.

You will build RAG pipelines, craft prompts, and implement evaluation frameworks to scale quality. This role collaborates with product designers and full‑stack engineers to ship customer‑facing features.