Sr Consultant

Job Summary

Senior hands-on AI engineer required to lead the design and delivery of enterprise GenAI solutions across retrieval-augmented generation, knowledge graphs, intelligent search, source-code analysis, document intelligence, AI-assisted data processing, and responsible AI workflows. The role requires strong ownership, proactive technical leadership, and the ability to work independently across complex and ambiguous problem areas.

Python, RAG/GraphRAG, LLM orchestration, knowledge graphs, vector search, document ingestion, source-code analysis, AI guardrails, human-in-the-loop workflows, data mapping, responsible AI

Key Responsibilities

• Lead the design and implementation of enterprise GenAI solution components from concept through to delivery.

• Build and enhance AI application pipelines covering data ingestion, retrieval, grounding, response generation, evaluation and monitoring.

• Design effective retrieval and search patterns across structured and unstructured information sources.

• Improve answer accuracy, consistency and business relevance through strong engineering design, grounding techniques and quality controls.

• Work with architects, developers, analysts and business stakeholders to translate complex business problems into practical AI engineering solutions.

• Support secure and scalable integration of AI capabilities into enterprise technology environments.

• Apply responsible AI principles, including privacy, security, transparency, auditability, fallback behaviour and human oversight where appropriate.

• Troubleshoot complex AI application issues, including retrieval gaps, poor context selection, inconsistent outputs and response quality concerns.

• Contribute to production readiness, including performance, scalability, monitoring, maintainability and operational support.

• Help define reusable engineering patterns that can be applied across multiple enterprise AI use cases.

• Provide technical leadership and guidance to support delivery teams and improve engineering quality.

Skill Requirements

• Strong hands-on experience in Python for backend, AI, automation, data engineering or cloud-native workloads.

• Proven experience designing and delivering LLM-powered or GenAI applications in enterprise environments.

• Strong understanding of retrieval-augmented generation, embeddings, vector search, prompt grounding and response generation.

• Experience working with structured and unstructured data sources, including documents, metadata, business artefacts or operational information.

• Experience designing AI solutions that are secure, auditable, explainable and suitable for enterprise use.

• Familiarity with cloud-native application design and modern engineering practices.

• Ability to troubleshoot complex AI application quality issues and identify practical remediation options.

• Strong ownership mindset with the ability to work independently, lead problem-solving and operate effectively without detailed task-level direction.

• Ability to communicate clearly with both technical and non-technical stakeholders.

Other Requirements

• Experience with GraphRAG, relationship modelling or advanced knowledge discovery patterns.

• Experience with AI evaluation, retrieval quality assessment, confidence scoring, feedback loops or response quality tuning.

• Experience with document understanding, information extraction, intelligent search or workflow automation.

• Experience working with complex enterprise systems, technical metadata or application modernisation initiatives.

• Exposure to source-code analysis, dependency mapping, application intelligence or similar technical analysis patterns.

• Experience with data mapping, data migration support, lineage, transformation rules or metadata-driven analysis.

• Experience designing AI-enabled workflows that include review, validation, exception handling or auditability.

• Experience working in regulated or large enterprise environments.

• Familiarity with one or more major cloud platforms and common cloud-native AI architecture patterns.

• Exposure to frontend development for AI-enabled applications is beneficial but not essential.