GenAI Engineer

About Role

We are seeking a highly skilled AI/ML Engineer to join our team and drive the implementation of cutting-edge ML solutions. The ideal candidate will have extensive experience in developing and deploying advanced GenAI applications, techniques and models.

Key Responsibilities:

1. Advanced RAG Implementation o Identify the most appropriate chunking techniques for a use case to maximize RAGs accuracy o Evaluate and implement different retrieval optimisation techniques depending on data & use case requirements o Apply RAG solutions to real-world use cases, ensuring practical applicability

2. LLM Fine-tuning and Optimization o Fine-tune Large Language Models (LLMs) for specific domain use cases o Work on creating the data & format required for fine tuning

3. AI Solution Development o Design and implement advanced AI solutions, including intent classification, sequential modeling, and semantic search o Work with vector databases & frameworks like LangChain to build LLMpowered applications

4. Model Evaluation and Improvement o Create robust evaluation benchmarks to assess model performance o Continuously research and propose innovative methods to enhance AI solution performance

5. Technical Leadership and Collaboration o Stay up-to-date with the latest developments in GenAI and share knowledge with the team o Collaborate with cross-functional teams to integrate AI solutions into production systems

Requirements:

2 years+ experience in Machine Learning and Natural Language Processing

Hands-on experience with PyTorch, Hugging Face Transformers, and other relevant libraries

Proven track record of implementing RAG systems for real-world use cases

Experience in fine-tuning and optimizing large language models

Proficiency in Python and software engineering best practices

Familiarity with vector databases and embedding techniques

Strong problem-solving skills and attention to detail

Passion for staying current with the latest GenAI developments