Prompt Engineer

You will be establishing and scaling prompt engineering as an IT capability that safely powers GenAI enabled solutions across the enterprise. At Deloitte.

Qualifications

• 5+ years in software engineering, with 2+ years in prompt engineering with proven expertise on patterns like Chain-of-Thought, Tree-of-Thought, self-consistence, prompt chaining and multi-model prompting;
• proven expertise in prompt strategies and techniques, RAG, embeddings and vector stores;
• excellent communication skills with an ability to steer, influence and convince senior leadership, particularly non-technologists;
• deep understanding of Microsoft’s ecosystem including Azure Cognitive Services, Semantic Kernel, Azure DevOps, GitHub, M365, AI Foundry, Power Platform and CoPilot Studio

What impact will you make?

You will lead large language model patterns, tooling, platforms, guardrails and integrate those into our DevSecOps, IT Service Management processes and ways of working. You will be driving GenAI adoption within the (personal) productivity domain, as well as enabling technology teams to integrate and utilize GenAI solutions. You will design the technology foundation bridging between (legacy) infrastructure and large language models, setting principles on interoperability, integration and orchestration.

For this role we do not offer visa sponsorship and/or relocation.

How do you do this?

• design task‑specific prompts and chains; apply prompt patterns and design Retrieval-Augmented Generation (RAG) logic for RAG scenarios;
• integrate Large Language Model (LLM) flows with enterprise APIs via function‑calling, agents, and workflow extensions, ensuring observability (logs, traces, monitoring);
• embed GDPR principles (data minimization, purpose limitation), access controls and DLP controls;
• align with EU AI Act obligations for high‑risk systems where applicable (data governance, transparency, human oversight);
• implement and adhere to Deloitte global standards, policies and guardrails assuring internal compliancy;
• engage with business and technology teams to prioritize use cases, track ROI and drive adoption;
• coordinate with cloud providers and model vendors, evaluate new capabilities and define enterprise feature enablement;
• evaluate and prioritize pre-built agents as part of the wider ecosystem of AI platforms and solutions.
• define and implement LLM Operations for continuous monitoring of model health, latency tracking, cost and response quality.

Benefits

• You will receive a profit-sharing bonus. On top of your fixed salary.
• Continue professional growth. Join our development program.
• A work-from-home office setup allowance to make sure you have everything you need for an ergonomically designed workstation and internet allowance.
• Work part-time (32 hours a week) or full-time (40-hours a week).
• in addition to a competitive salary, a share in our profits
• great growth opportunities. Depending on your ambitions and performance
• a development program that helps you keep growing
• flexible working hours and the opportunity to work from home
• 26 days of paid holiday annually, and the opportunity to purchase 15 additional holiday days annually
• a 32 or 40-hour working week
• the opportunity to take a month of unpaid leave once annually
• the possibility to go on sabbatical for at least 2 months
• a good mobility scheme: choice between a company car with a fuel pass for Europe or the Mobility+ option or a gross cash option with which you arrange all your own transport or a public transport annual subscription
• an iPhone, which is also for personal use
• a laptop with a 4G connection
• a good pension scheme
• an opportunity to take part in our collective health insurance scheme
• an opportunity to benefit from tax-efficient facilities, such as company fitness and a bicycle scheme