Generative AI Engineer: RAG, LLMs & AI API Builder

Spait Infotech; United Kingdom; On-site; GBP 60,000 - 90,000; Full time

Job summary

Spait Infotech is seeking a skilled AI/ML engineer to develop and integrate Generative AI and LLM applications for business needs. You will design RAG pipelines, work with embeddings and vector databases, and build backend services using Python and FastAPI.

You'll collaborate with data scientists and software engineers to deploy AI solutions on cloud platforms like AWS, Azure or GCP, and continuously evaluate model outputs, enforce security, and optimize performance.

Qualifications

• Strong Python programming.
• Solid knowledge of Machine Learning, NLP and Deep Learning.
• Experience with LLMs, RAG, embeddings, and prompt engineering.
• Knowledge of LangChain, LlamaIndex, or similar.
• Experience with REST APIs and Git.
• Understanding of databases and vector databases.
• Familiarity with Docker and cloud deployment.

Responsibilities

• Develop and integrate Generative AI/LLM applications.
• Build RAG pipelines using embeddings, vector databases, and document processing.
• Work with models such as GPT, Claude, Gemini, Llama.
• Develop effective prompt engineering strategies and evaluate model outputs.
• Build AI agents and tool-calling workflows.
• Develop APIs and backend services using Python/FastAPI or similar frameworks.
• Work with vector databases such as Pinecone, FAISS, Weaviate, or Chroma.
• Implement model evaluation, monitoring, security, and optimization.
• Collaborate with data scientists, software engineers, and product teams.
• Deploy AI solutions using cloud platforms such as AWS, Azure, or GCP.

Skills

Python

Machine Learning

NLP

Deep Learning

LLMs

RAG

Embeddings

REST APIs

Git

Docker

Cloud deployment

Tools

LangChain

LlamaIndex

Pinecone

FAISS

Weaviate

Chroma

FastAPI

Job description

Spait Infotech is seeking a skilled AI/ML engineer to develop and integrate Generative AI and LLM applications for business needs. You will design RAG pipelines, work with embeddings and vector databases, and build backend services using Python and FastAPI.

You'll collaborate with data scientists and software engineers to deploy AI solutions on cloud platforms like AWS, Azure or GCP, and continuously evaluate model outputs, enforce security, and optimize performance.