Deep AI/Agentic Engineer

Consol Partners; Greater London; On-site; GBP 80,000 - 100,000; Full time

Job summary

A private equity-backed firm is seeking a deep AI/Agentic Engineer to lead the design and delivery of complex AI-native engagements. The ideal candidate will have 6–8 years of experience in software/application or AI engineering and will be responsible for building production-grade AI systems. Key skills include proficiency in Python, multi-agent systems, and familiarity with cloud AI ecosystems. This role offers an opportunity to shape enterprise outcomes and enhance engineering capabilities.

Qualifications

• 6-8 years in Software/application engineering, AI engineering, or applied data engineering.
• Strong experience with LLMs, embeddings, RAG, retrieval stacks, and vector stores.
• Hands-on experience in multi-agent systems, agent orchestration, or MCP-like tool patterns.
• Proficiency in Python, including ability to build production-grade workflows.
• Experience with at least one cloud AI ecosystem (Azure/OpenAI, GCP/Vertex, Anthropic, AWS etc.).
• Familiarity with semantic modelling, ontologies, or knowledge graph thinking.

Responsibilities

• Design and build production-grade AI systems using LLM applications.
• Develop multi-agent architectures including planning and monitoring.
• Implement retrieval and vector-based systems with embeddings and structured reasoning.
• Enable precise reasoning and data alignment through ontology and knowledge modelling.
• Integrate and automate API workflows, tools, and enterprise connectors.

Skills

Software/application engineering

AI engineering

Data engineering

LLMs and embeddings

Multi-agent systems

Python

Cloud AI ecosystems

Semantic modelling

Job description

Our client are a private equity backed firm who are looking for a deep AI/Agentic Engineer to lead the design and delivery of the organisations complex AI-native engagements, from agentic systems to semantic layers. Pair hands‑on technical leadership with client trust, shaping both enterprise outcomes and the firm's long‑term engineering capability.

Responsibilities:

You will design and build production‑grade AI systems across:

• LLM applications using modern orchestration patterns, prompt frameworks, and evaluation loops.
• Multi-agent architectures, including planning, delegation, safety constraints, and monitoring.
• Retrieval & vector‑based systems, embeddings, structured reasoning, and semantic workflows.
• Ontology & knowledge modelling literacy, enabling more precise reasoning and data alignment.
• Integrations & automation, including API workflows, tools, and enterprise connectors.

Skills:

• 6-8 years in Software/application engineering, AI engineering, or applied data engineering.
• Strong experience with LLMs, embeddings, RAG, retrieval stacks, and vector stores.
• Hands‑on experience in multi‑agent systems, agent orchestration, or MCP‑like tool patterns.
• Proficiency in Python, including ability to build production‑grade workflows.
• Experience with at least one cloud AI ecosystem (Azure/OpenAI, GCP/Vertex, Anthropic, AWS etc.).
• Familiarity with semantic modelling, ontologies, or knowledge graph thinking – literacy required, mastery a bonus.