AI Engineer (NLP)

Location: Remote (Anywhere) – Preference for candidates within the European Economic Area (EEA)

About the Client:

The client is a forward-thinking organization specializing in cutting-edge technologies and applied research. As part of their ongoing projects, they are looking for a highly skilled Technical Specialist to support their March work package, focused on researching, comparing, and demonstrating advanced Retrieval-Augmented Generation (RAG) techniques. The goal is to compare naive RAG approaches with a blend of state-of-the-art (SOTA) and novel techniques, using existing source data that includes legal texts, government regulations, and court cases.

This is a great opportunity for someone with deep expertise in applied Large Language Models (LLMs) and RAG, who enjoys both theoretical research and hands-on development.

Job Description:

The client seeks a highly qualified Technical Specialist with expertise in LLMs, RAG techniques, and NLP to take ownership of this work package while the rest of the team focuses on other priorities.

You will be responsible for:

• Conducting research to compare naive RAG methods with advanced SOTA and experimental approaches.

• Developing demonstrator code to showcase performance differences between different RAG techniques.

• Utilizing existing datasets (primarily PDF documents) to build and optimize RAG workflows.

• Applying NLP and LLM-based techniques for document processing, retrieval, and knowledge graph integration.

• Constructing and optimizing Knowledge Graphs using NLP/LLM-assisted techniques.

• Benchmarking LLM models and RAG workflows to evaluate effectiveness.

• Collaborating with the internal team to integrate findings into the broader project.

Required Qualifications & Experience:

The ideal candidate must have:

• A Master’s or PhD in Data Science, Machine Learning, Artificial Intelligence, or a closely related field.

• Strong practical experience in applied LLMs and RAG techniques.

• Experience in serving Open Source Software (OSS) LLMs in production.

• Knowledge of Supervised Fine-Tuning (SFT) and Data Preprocessing Optimization (DPO).

• Hands-on experience in data preparation for large-scale NLP applications.

• Expertise in Graph RAG and Knowledge Graph construction (NLP/LLM-assisted).

• Practical experience in function calling and tool usage within LLM frameworks.

• Experience with multi-modal LLMs (text, audio, images).

• Proficiency in Python programming for machine learning and NLP applications.

• Strong skills in benchmarking and optimizing LLM models.

Desirable Skills & Experience:

Familiarity with any of the following would be a plus:

• Prompt Engineering and optimization techniques.

• Test-Time Preference Optimization (TPO).

• KV Cache-stuffing and compression techniques for LLMs.

• LLM observability tools and best practices.

• Model distillation for optimization and deployment.

• Personal Information Masking and Reconstruction techniques.

• Test-time autoscaling and batching for model efficiency.

• Version control (Git) and checkpointing for model management.

Additional Requirements:

• Candidate must be located within the European Economic Area (EEA).

• Strong communication skills and ability to work independently on research and development tasks.

Start Date & Duration:

• Start Date: March 2025 (exact date TBD)

• Duration: Temporary/Contract, with a possibility of extension depending on project needs.

Why You Should Apply:

This is an opportunity to work at the forefront of LLM and RAG research and contribute to innovative AI applications in legal and government data processing. You’ll be part of a dynamic, research-driven environment where your expertise will directly influence the development of new AI techniques.

Commitment to Diversity, Equity, and Inclusion:

The client is committed to fostering a diverse, equitable, and inclusive work environment. They encourage candidates from all backgrounds to apply.