Job Description: Our public sector client is seeking an AI Engineer to work on an innovative project harnessing AI and data analytics. The AI Engineer will be assigned to high complexity work and will fully participate in activities that support the team's delivery and continuous improvement.
Key Responsibilities:
- Build and query knowledge graphs to represent structured knowledge and relationships, particularly in the context of enhancing retrieval-augmented generation (RAG) models.
- Implement and fine-tune RAG models, combining retrieval-based and generative approaches to improve AI's ability to generate contextually relevant and accurate responses.
- Apply information retrieval (IR) techniques for implementing document or knowledge retrieval systems that form the basis of RAG.
- Preprocess and manipulate graph data for tasks like entity resolution, graph pruning, and graph-to-text generation.
- Utilize distributed training techniques for large generative models, especially when using graph data that may require massive computational resources.
- Build and fine-tune graph embeddings and sentence embeddings that capture semantic relationships within graph-based structures.
- Evaluate retrieval-augmented models through both precision/recall of retrieved information and relevance of generated output.
- Deploy graph-based AI models in production environments using cloud platforms (Azure), ensuring scalability and low-latency retrieval.
Deliverables
- Requirements, design, build and configuration, and sustainment documents.
- Status reports, operational KPIs, service performance metrics, production risks, and issues management.
- Resource forecasting and planning.
- Digital Service reliability and stability decision recommendations.
Required Skills:
- Familiarity with graph databases such as Neo4j, ArangoDB, or Amazon Neptune.
- Experience with embedding-based search, nearest neighbour search, and indexing techniques using libraries like FAISS, Annoy, or Elasticsearch.
- Knowledge of graph-based algorithms such as PageRank, centrality measures, and community detection.
- Familiarity with optimization methods, including gradient-based optimization and multi-task learning.
- Proficiency with vector databases and embedding management tools like CosmosDB or Pinecone.
- Strong understanding of performance metrics for generative AI models, including BLEU, ROUGE, perplexity, and generation quality.
- Familiarity with cloud platforms (Azure) for deploying graph-based AI models in production environments.
- Proficiency in programming languages like Python, or other languages commonly used in AI.
- Knowledge of transfer learning techniques to leverage existing models and datasets for improved task performance.
- Knowledge of ETL processes for data wrangling, preparing data for graph databases, and integrating various data sources.
Affinity Earn:
Know someone who’s great for this, or any of our open roles? Earn up to $4,000/year for each successful referral through Affinity Earn. You can also earn up to $50,000 for helping us find new clients. Learn about our referral program at https://affinity-group.ca/earn/ or browse our jobs & follow us at https://www.linkedin.com/company/affinity-staffing/jobs/
About Affinity:
Affinity Group is a technology and business consulting and services company. We believe in creating long term relationships between clients and consultants that foster a mutually beneficial partnership. Affinity is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All employment is decided on the basis of qualifications, merit and business need.
For more information on Affinity, please visit www.affinity-group.ca
Job Number: 11807
