Prompt Engineer

Il y a 6 heures

Brussels, Brussels, Belgique Tata Consultancy Services Temps plein

Role: Prompt Engineer

📍 Location: Brussels, Belgium

🏢 Company: Tata Consultancy Services (TCS) Belgium

📅 Employment Type: Full-time


About the Role

We are looking for a highly skilled Prompt Engineer to design, develop, and optimize advanced AI solutions leveraging Large Language Models (LLMs). The ideal candidate will have hands-on experience in prompt engineering, Retrieval-Augmented Generation (RAG), LLM fine-tuning, AI evaluation frameworks, and responsible AI practices.

You will work closely with cross-functional teams to build scalable, secure, and business-oriented generative AI solutions that deliver measurable impact.


Key Responsibilities

  • Design, develop, and refine sophisticated prompt strategies for Large Language Models (LLMs).
  • Architect, test, and optimize prompts to improve accuracy, relevance, creativity, and cost-efficiency.
  • Develop and maintain Retrieval-Augmented Generation (RAG) solutions leveraging proprietary knowledge sources.
  • Build, curate, and manage knowledge bases and datasets for AI applications.
  • Fine-tune pre-trained LLMs using techniques such as LoRA, QLoRA, and PEFT.
  • Develop evaluation frameworks and metrics to assess AI model and prompt performance.
  • Design and implement multi-step prompt chains and AI workflows to automate business processes.
  • Analyze model failures and mitigate risks such as hallucinations, bias, and prompt injection attacks.
  • Implement AI guardrails, validation mechanisms, and responsible AI controls.
  • Stay updated with the latest advancements in Generative AI, Prompt Engineering, and LLM technologies.


Required Skills & Experience

  • Strong understanding of NLP fundamentals and Large Language Model architectures.
  • Expertise in advanced prompting techniques including:
  • Zero-shot prompting
  • Few-shot prompting
  • Chain-of-Thought (CoT)
  • Self-Consistency
  • Tree-of-Thoughts
  • Experience developing end-to-end RAG solutions using vector databases such as Pinecone, Weaviate, or pgvector.
  • Hands-on experience with LLM fine-tuning techniques including LoRA and QLoRA.
  • Strong Python programming skills and experience with AI platforms and APIs.
  • Knowledge of LangChain, LlamaIndex, or similar AI orchestration frameworks.
  • Experience with AI evaluation platforms such as LangSmith, MLflow, or equivalent.
  • Familiarity with Azure OpenAI, AWS Bedrock, Google Vertex AI, or related cloud AI platforms.
  • Understanding of software engineering principles, scalability, and maintainability.
  • Knowledge of Responsible AI, AI ethics, security practices, and cybersecurity threats related to LLMs.


Preferred Certifications

One or more of the following certifications is an advantage:

  • NVIDIA Generative AI LLMs Certification
  • Microsoft Azure AI Engineer Associate
  • AWS Certified Machine Learning Specialty
  • Equivalent industry-recognized certification


Soft Skills

  • Strong communication and stakeholder management skills.
  • Ability to collaborate in multicultural and multilingual environments.
  • Self-driven, proactive, and results-oriented mindset.
  • Ability to work independently and within cross-functional teams.
  • Knowledge of DevSecOps and automation best practices.
  • Fluent in English & one of French or Dutch is a must.