AI Lead Engineer

Vallum Associates; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Vallum Associates in London is seeking an AI Lead Engineer for a contract role, onsite two days a week. You will design agentic AI architectures and orchestrate multi-agent systems with LLMs, tooling, and memory management to support enterprise platforms.

You will define reference architectures for systems of record, ensure auditability with logs and provenance, and select/frameworks (LangGraph, Google ADK, MCP, A2A) while collaborating with engineers to deliver MVPs for customer banking use

Qualifications

• Design agentic AI architectures with multi-agent patterns.
• Define reference architectures for enterprise AI platforms with LLMs and SOR.
• Design audit-ready agent interactions, logs and provenance.
• Select and standardize AI frameworks (LangGraph, Google ADK, MCP, A2A).
• Hands-on expertise with orchestrator frameworks.
• Experience with LLMs, prompt engineering, tool/function calling, memory management.
• Exposure to AI quality metrics: task success rate, groundedness, containment, FCR.
• Experience on Google Cloud Platform (preferred) or equivalent hyperscale.
• Deep understanding of LLMs, generative AI, RAG, embeddings, and prompt/guardrail engineering.

Responsibilities

• Design agentic AI architectures using multi-agent orchestration patterns.
• Define reference architectures for enterprise agent platforms integrating LLMs with SOR.
• Design audit-ready agent interactions, tool usage logs, and decision provenance.
• Select and standardize frameworks (e.g., LangGraph, Google ADK, MCP, A2A patterns).
• Hands-on expertise with agentic orchestrators.
• Work with LLMs, prompt engineering, tool calls, memory management.
• Monitor AI quality metrics such as task success rate and containment.
• Leverage cloud platforms (GCP preferred) for scalable AI solutions.
• Architect end-to-end AI/ML systems including data ingestion, training, deployment and monitoring.

Skills

Agentic AI architectures

Multi-agent orchestration

LLMs integration

Prompt engineering

Tool usage logging

Memory management

GCP experience

Tools

LangGraph

Google ADK

MCP

A2A patterns

Job description

Role : AI Lead Engineer

Location: London, UK

Type of Role: Contract

Mode of work: 2 Days onsite in Week

( Exp Range 9+)

JD:

• Design agentic AI architectures using multi‑agent orchestration patterns (planner‑executor, supervisor‑worker, tool‑using agents).
• Define reference architectures for enterprise agent platforms integrating LLMs with systems of record (core banking, CRM, risk, payments).
• Design audit‑ready agent interactions, tool usage logs, and decision provenance.
• Select and standardize frameworks (e.g., LangGraph, Google ADK, MCP, A2A patterns).
• Hands‑on expertise with agentic frameworks (orchestrators).
• Experience with LLMs, prompt engineering, tool/function calling, memory management.
• Exposure to AI quality metrics: task success rate, groundedness, containment, FCR.
• Experience on Google Cloud Platform (preferred) or equivalent hyperscale.
• Deep understanding of LLMs, generative AI, RAG patterns, vector databases, embeddings, and prompt/guardrail engineering.

Desirable skills/knowledge/experience: (As applicable)

• Build Production Grade Agentic AI applications and necessarily have navigated through security, governance and performance management of the end to end model.
• Strong understanding of regulated financial services environments.
• Proven experience implementing AI risk controls, model governance, and auditability.
• Strong experience designing end‑to‑end AI/ML architectures, including data ingestion, feature engineering, model training, deployment, and monitoring.
• Hands‑on expertise with cloud AI platforms (GCP).
• Strong knowledge of LLMOps practices, including CI/CD for models, model registries, feature stores, lineage tracking, and observability.
• Experience architecting scalable real‑time, batch, and streaming inference systems with clear performance and reliability requirements.
• Familiarity with secure cloud patterns, IAM, VPC design, and data protection.
• Work with solution Architect and implement design along with team of engineers to ensure MVP delivered for Customer business banking usecases in onboarding / Credit assist