Senior Prompt Engineer

Mastek; Reading; On-site; GBP 90,000 - 120,000; Full time

Job summary

Mastek is seeking a Senior Prompt Engineer to lead the design, optimisation, and scaling of prompting strategies for large language models in enterprise contexts. You will collaborate with engineering teams to integrate prompts into application workflows, autonomous agents, and RAG pipelines, while improving performance, reducing latency, and ensuring output safety and consistency.

This role demands hands-on development, evaluation, and governance of prompts with reusable templates and robust

Qualifications

• 5+ years of software engineering with 2+ years in production-level prompt engineering.
• Strong expertise in LLMs (GPT-4, Claude, Llama, Mistral, Nova or similar).
• Proficient in Python and/or Java.
• Experience with AI orchestration frameworks and prompt evaluation/monitoring tools such as LangChain, LangSmith, Fiddler, InspectAI, OpenAI Evals.

Responsibilities

• Design and implement advanced, dynamic prompts tailored to business use cases.
• Optimise LLM performance by reducing token consumption, latency, and hallucinations.
• Integrate prompts into agent-based systems, APIs, and RAG architectures.
• Develop prompt frameworks and reusable templates for scalable deployment.
• Establish evaluation, benchmarking, and regression testing mechanisms.
• Implement guardrails to mitigate prompt injection and unsafe outputs.
• Collaborate with product and engineering to translate business requirements into technical prompt logic.
• Maintain a version-controlled prompt repository with continuous improvements.

Skills

Prompt engineering

LLM experience

Python or Java

Software development

Education

Bachelor/Master in CS or related field

Tools

LangChain

LangSmith

Fiddler

InspectAI

OpenAI Evals

Job description

We are looking for a Senior Prompt Engineer to lead the design, optimisation, and scaling of advanced prompting strategies for large language models (LLMs). This role focuses on delivering context-aware, safe, and efficient AI outputs across complex enterprise use cases.

You will work closely with engineering teams to integrate prompts into application workflows, autonomous agents, and RAG pipelines, while continuously improving performance, reducing latency, and ensuring output consistency.

Key Responsibilities

• Design and implement advanced, dynamic prompts tailored to business-specific use cases
• Optimise LLM performance by reducing token consumption, latency, and hallucinations
• Integrate prompts into agent-based systems, APIs, and RAG architectures
• Develop prompt frameworks and reusable templates for scalable deployment
• Establish evaluation, benchmarking, and regression testing mechanisms
• Implement guardrails to mitigate prompt injection and unsafe outputs
• Collaborate with product and engineering teams to translate business requirements into technical prompt logic
• Maintain a version-controlled prompt repository with continuous improvements

Required Skills & Experience

• 5+ years in software engineering with 2+ years in production-level prompt engineering
• Strong expertise in LLMs: GPT-4, Claude, Llama, Mistral, Nova (or similar)
• Advanced programming skills in Python and/or Java
• Experience with AI orchestration frameworks such as:
• LangChain
• Hands-on experience with prompt evaluation and monitoring tools, such as:
• LangSmith
• Fiddler
• InspectAI
• OpenAI Evals

Preferred Qualifications

• Bachelor’s or Master’s degree in Computer Science, AI, Statistics, Cognitive Science, or related quantitative fields