LLM Customisation

Job Title: LLM Customisation & Prompt Engineering Specialist

About Brainwave Science:

Brainwave Science

is a leader in cognitive technologies, specializing in solutions for the security and intelligence sectors. Our flagship product,
iCognative

, leverages real-time cognitive response analysis using Artificial Intelligence and Machine Learning techniques to redefine the future of investigations, defense, counterterrorism, and counterintelligence operations. Beyond security,
Brainwave Science

is at the forefront of healthcare innovation, applying our cutting-edge technology to identifying diseases, various neurological conditions, and mental health challenges in advance and identification of stress and anxiety in real time and providing non-medical, science-backed interventions. Together, we are shaping a future where advanced technology strengthens security, promotes wellness, and creates a healthier, safer world for individuals and communities worldwide. 

Role Overview

I
n this role, you will be responsible for customising large language models (LLMs) to align with our business needs, developing effective prompt strategies, and ensuring that the models deliver accurate, safe, and context-aware outputs. You will collaborate with data scientists, engineers, and product managers to integrate LLMs into our applications and continuously enhance their performance. 

Key Responsibilities

• Design, test, and refine prompts, chains, and workflows to achieve high-quality results from LLMs.
• Fine-tune and customise pre-trained LLMs (OpenAI, Anthropic, LLaMA, Mistral, etc.) on domain-specific datasets.
• Implement evaluation metrics to measure prompt effectiveness, response accuracy, and model reliability.
• Collaborate with engineering teams to integrate LLMs into production environments.
• Research and apply the latest techniques in prompt engineering, retrieval-augmented generation (RAG), few-shot/zero-shot learning, and model alignment.
• Establish guardrails and safety mechanisms to prevent harmful or biased outputs.
• Document best practices and build internal guidelines for effective prompt usage.

Requirements

• Proven experience in LLM prompt engineering, fine-tuning, or customization.
• Hands-on experience with frameworks such as LangChain, LlamaIndex, Haystack, or similar.
• Proficiency in Python and experience with ML libraries (PyTorch, TensorFlow, Hugging Face Transformers).
• Strong understanding of natural language processing (NLP) concepts and LLM architectures.
• Ability to analyze and optimize model outputs for accuracy, consistency, and safety.
• Familiarity with cloud platforms (AWS, GCP, Azure) and MLOps practices is a plus.
• Excellent communication skills and ability to translate technical work into business impact.

Preferred Qualifications

• Experience with fine-tuning open-source LLMs (LLaMA, Falcon, Mistral, etc.).
• Background in information retrieval, vector databases (Pinecone, Weaviate, FAISS).
• Knowledge of evaluation frameworks for LLMs (HELM, OpenAI Evals, Ragas, etc.).
• Previous work in AI productization or enterprise-level AI solutions.

What We Offer

• Competitive compensation based on experience
• Flexible working hours and remote-friendly culture
• Access to high-performance compute infrastructure
• Opportunities to work on groundbreaking AI projects in healthcare, security, and defense