Generative AI / LLM Engineer

Salt; Brussel; Hybride; EUR 80 000 - 120 000; Temps partiel

Résumé du poste

Salt is seeking a hands-on Generative AI / LLM Engineer for a major multi-year public sector programme in Brussels. The role focuses on design, development, integration and deployment of enterprise Generative AI and Conversational AI solutions, including RAG, LangChain and embeddings.

You will contribute across the AI lifecycle, delivering AI-powered applications and services in secure, scalable production environments within a hybrid setup (2 days onsite in Brussels per week).

Qualifications

• Hands-on experience delivering Generative AI/LLM solutions in a professional environment.
• Experience designing and deploying enterprise AI applications and services.
• Strong Python development and data integration capabilities.

Responsabilités

• Designing and developing Generative AI and LLM-powered applications.
• Building and integrating enterprise Conversational AI and Chatbot solutions.
• Developing AI applications using Python and integrating LLMs into enterprise platforms.
• Designing and implementing Retrieval-Augmented Generation (RAG) solutions.
• Developing prompts and embeddings with vector-search capabilities.
• Working with APIs, data sources, and enterprise applications for LLM services.
• Ensuring AI security controls and governance practices are in place.

Connaissances

Generative AI

Python

LangChain

RAG

Prompt engineering

LLM APIs

Embeddings

Vector search

Conversational AI

AI governance

AI security

Outils

NeMo Guardrails

REST APIs

GraphQL

SQL/NoSQL

OAuth2/JWT

Git

Microservices

Description du poste

Onsite: 2 days per week in Brussels

Contract: Freelance / Contract

Programme: Multi-year Public Sector Programme

Seniority: Junior / Medior / Senior

The Opportunity

We are looking for Generative AI / LLM Engineers to join a major multi-year technology programme for a large public-sector organisation in Brussels.

This is a hands-on engineering opportunity focused on the design, development, integration and deployment of enterprise Generative AI, Large Language Model (LLM) and Conversational AI solutions.

You will work across the AI lifecycle, helping take Generative AI use cases from initial design and experimentation through to secure, scalable production environments.

The programme will involve technologies and concepts including Python, LangChain, RAG, LLM APIs, prompt engineering, embeddings, vector search, Conversational AI, AI security and governance.

We are interested in engineers who have worked with Generative AI or Conversational AI in a professional environment and can demonstrate practical experience delivering AI-powered applications and services.

Key Responsibilities

Depending on your level of experience, you will be involved in:

• Designing and developing Generative AI and LLM-powered applications.
• Building and integrating enterprise Conversational AI and Chatbot solutions.
• Developing AI applications and services using Python.
• Integrating commercial and/or open-source Large Language Models into enterprise platforms.
• Designing and implementing Retrieval-Augmented Generation (RAG) solutions.
• Developing solutions using frameworks such as LangChain.
• Designing and optimising prompts for enterprise AI use cases.
• Implementing embeddings and vector-search capabilities.
• Developing integrations between LLM services, enterprise applications, APIs and data sources.
• Designing dialogue flows and conversational experiences.
• Developing validation mechanisms to improve the quality and reliability of LLM outputs.
• Benchmarking and evaluating LLM performance.
• Implementing appropriate AI security controls and guardrails.
• Supporting AI governance and responsible AI practices.
• Working with architecture, infrastructure, UX/UI and engineering teams.
• Supporting solutions through development, testing, deployment and production.
• Contributing to the continuous improvement of AI applications based on user feedback and performance data.

Generative AI & LLM Experience

We are particularly interested in candidates with hands-on experience across several of the following:

• Generative AI
• Python
• LangChain
• Retrieval-Augmented Generation (RAG)
• Prompt Engineering
• LLM APIs
• Open-source LLMs
• NLP
• Transformers
• Embeddings
• LLM evaluation and benchmarking
• AI security
• AI governance
• LLM guardrails
• Responsible AI

Experience with technologies or frameworks such as NeMo Guardrails would also be beneficial.

Conversational AI

As Conversational AI forms an important part of the programme, experience with enterprise Chatbot or virtual-assistant solutions would be particularly valuable.

This could include:

• Conversational AI platforms
• Dialogue and conversation-flow design
• Rasa
• Botpress
• Voiceflow
• Training and annotation datasets
• Conversational UX
• Chatbot testing and optimisation
• Feedback analysis
• A/B testing
• Tone-of-voice and conversational content

You do not necessarily need to have worked with every technology listed, but you should be able to demonstrate relevant experience delivering AI, LLM or Conversational AI solutions in a professional environment.

The wider technical environment includes modern enterprise application development and integration.

Relevant experience may include:

• REST APIs
• GraphQL
• SQL / NoSQL databases
• OAuth2 / JWT
• Git / branching
• Microservices
• Event-driven architecture
• Cloud-native applications
• API security

Ways of Working

You will work within multidisciplinary Agile teams and collaborate with stakeholders across AI, engineering, architecture, infrastructure, UX and business functions.

Experience or understanding of the following would therefore be beneficial:

• Agile / Scrum
• Design Thinking
• DevOps
• CI/CD
• Design systems
• ITIL or similar service-management methodologies
• Working within large enterprise production environments

Strong communication skills are important, particularly the ability to explain technical AI concepts clearly and collaborate with both technical and non-technical stakeholders.

Experience Levels

Applications are welcomed across three levels:

Junior: More than 1 year of relevant professional experience

Medior: More than 3 years of relevant professional experience

Senior: More than 5 years of relevant professional experience

Your CV should clearly demonstrate relevant projects involving Generative AI, LLMs, Chatbots, Conversational AI or related AI technologies.

For Senior candidates in particular, we are looking for strong evidence of delivering enterprise AI solutions into production rather than purely academic or experimental AI experience.

Mandatory Language Requirements

Candidates must have:

French OR Dutch – Very Good

AND

English – Very Good

Unfortunately, candidates who only speak English cannot be considered for this opportunity.

Working Arrangement

This is a hybrid engagement based in Brussels, requiring approximately 2 days per week onsite.

The opportunity forms part of a multi-year public-sector technology programme, making it particularly attractive to candidates looking for the potential of a longer-term engagement while working with modern Generative AI and LLM technologies.