SUMMARY:
ESSENTIAL SKILLS:
Architect and deliver production-grade AI systems spanning classical ML, LLM pipelines, RAG, agentic
orchestration, and context engineering.
Design and implement retrieval-augmented generation (RAG) architectures, including semantic caching,
contextual compression, hybrid retrieval and embedding pipelines.
Provide consultation on the architecture of agentic systems, including tool-calling architectures, multi-agent
workflows, agent memory design, and human-in-the-loop integration.
Develop and optimize large language model (LLM) capabilities: prompt and context engineering, fine-tuning,
LLM orchestration, and document intelligence workflows.
MLOps and delivery: model deployment, inference gateways, intelligent routing, monitoring, governance, and
performance optimisation for production systems.
Data engineering and production-scale processing: PySpark, ETL/ELT pipelines, API ingestion, unstructured
data processing, vector stores, and scalable embedding generation pipelines.
ADVANTAGEOUS SKILLS:
Experience implementing governance, security and compliance measures for AI in regulated, high-impact
domains.
Knowledge of BI and visualization tools (e.g., Power BI, Grafana, AWS QuickSight) to surface model outputs
and monitoring metrics.
Familiarity with LLM agents, RAG pipelines and retrieval tooling for document intelligence solutions.
Experience with CI/CD and automation tools such as GitHub Actions and orchestration platforms for model
lifecycle management.
Background in prompt engineering and contextual window design for cost-effective inference and improved
relevance.
Experience coaching teams and delivering training to promote adoption of AI solutions across business units.
Prior experience in AI ethics, bias mitigation, and explainability for enterprise-grade models.
POSITION INFO:
ROLE & RESPONSIBILITIES:
Lead design and delivery of end-to-end AI solutions including classical ML models, LLM pipelines, RAG
systems, and multi-agent orchestration.
Provide architectural consultation for agentic systems, advising on tool-calling patterns, agent coordination
(A2A), memory design, and human-in-the-loop workflows.
Design context windows, prompt strategies, and contextual compression techniques to optimise LLM relevance
and cost.
Implement document intelligence solutions leveraging embeddings, vector stores, and hybrid retrieval
strategies.
Architect and build agentic systems: tool-calling architectures, multi-agent workflows, agent memory, and
human-in-the-loop pathways.
QUALIFICATIONS/EXPERIENCE:
Bachelor's degree in Computer Science, Data Science, Mathematics or equivalent experience, with strong
background in mathematics and analytical problem solving.
Proven track record of leading teams, platforms and enterprise deployments handling millions of records in
regulated, high-impact environments.
Deep hands-on experience across the full lifecycle of modern LLM applications: design, implementation,
orchestration, deployment and operational monitoring.
Submit your CV to: and Subject line Role title
