About RVS
Our client, Royal Voluntary Service (RVS), is a leading UK charity managing one of the largest networks of volunteers across the country to deliver essential healthcare, homelessness, and food security services. RVS is embarking on an exciting digital transformation and hiring their first-ever tech team out of South Africa in their 80-year history.
The Opportunity
They are seeking an experienced Data Engineer with expertise in vector search and embeddings to join RVS's growing technology team. You'll play a critical role in developing a vector-based search capability that powers our volunteer matching platform, connecting volunteers with opportunities that match their interests and skills.
This is a greenfield opportunity where you'll implement vector search functionality in a pre-established infrastructure environment, with support from a full engineering team handling the surrounding components.
What You Will Be Building:
- Create and optimize a system to match volunteer searches with relevant opportunities using vector similarity.
- Implement summarization of volunteer opportunity descriptions and generate vector embeddings.
- Develop systems that interpret natural language queries to find conceptually related volunteer opportunities.
- Connect your search capabilities with pre-built backend services and data structures.
Your Day-to-Day Responsibilities:
- Implement and fine-tune language models for text summarization (we're considering Llama 3 or similar open-source models).
- Generate and optimize text embeddings from opportunity descriptions
- Set up and configure vector databases (such as ChromaDB, Pinecone, or enhanced vector capabilities in Postgres/MongoDB).
- Develop and document efficient vector search algorithms and pipelines.
- Collaborate with the existing engineering team on integration points.
- Research and recommend appropriate technologies based on our specific needs.
- Continuously optimize search capabilities for improved accuracy.
What Success Looks Like:
- Within your first year, you will have implemented a production-ready vector search system that helps volunteers find the perfect opportunities, supporting RVS's mission to deliver critical services across the UK.
Requirements
Our Ideal Candidate Has :
- Technical Skills & Experience:
- 5+ years of software engineering experience, with a focus on data pipelines and backend systems. Strong Python proficiency with experience in libraries such as Pandas, NumPy.
- Hands-on experience with vector databases or search technologies.
- Familiarity with language models and embedding generation.
- Experience with containerization (Docker) and understanding of microservices architecture. Knowledge of cloud environments (preferably Azure).
- Specialized Knowledge:
- Experience with open-source LLMs like Llama 3 or similar models.
- Knowledge of Parameter-Efficient Fine-Tuning (PEFT) techniques.
- Familiarity with vector databases such as ChromaDB, Pinecone, or vector capabilities in traditional databases.
- Experience with text processing libraries (NLTK, spaCy, HuggingFace).
- Qualities We Value:
- Self-starter mentality, comfortable in a greenfield environment.
- Strong problem-solving abilities and analytical thinking.
- Willingness to learn new technologies and approaches.
- Ability to communicate complex technical concepts to non-technical stakeholders.
- Passion for using technology to make social impact.
Benefits
In addition to a competitive salary we have additional perks including:
- A healthcare stipend
- IT equipment (laptop, monitor, etc)
- Opportunity to contribute to meaningful social impact through technology
- Professional growth in cutting-edge AI/ML technologies
- Collaborative, inclusive team culture that values diverse perspectives
About The Team
You'll be joining a newly formed engineering team working on a greenfield project. The underlying infrastructure (Azure), relational database structure, and surrounding services are already established or in development. Your focus will be specifically on implementing the vector search capabilities within this ecosystem.
This is an ideal role for an experienced engineer looking to apply or grow their skills in AI/ML and vector search technologies while making a meaningful social impact.
