Senior AI Systems Engineer

Financial Conduct Authority

. Build and operate production-grade AI systems using foundation models, retrieval, tool-use and workflow services for regulatory challenges .

Posted 9/29/2026full-timeLondon • United KingdomSenior💰 £53,800 - £88,600 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and operating production-grade AI systems, with a focus on model integration, retrieval-augmented generation, and workflow orchestration. Proficient in implementing secure engineering practices and evaluating AI system performance within regulatory environments.

Highest-signal resume keywords

Python ProgrammingProduction Software EngineeringAI System EvaluationCI/CD ImplementationAWS Bedrock

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Foundation ModelsLLM APIsRetrieval PipelinesSemantic SearchAutomated TestingCloud-Native ServicesEvidence-Grounded WorkflowsOperational TelemetryAccess ControlData Leakage Prevention

Soft Skills

Technical CommunicationCollaborationKnowledge Transfer

Tools & Technologies

AgentCoreGraph-Enhanced RetrievalEvent-Driven Systems

Industry Keywords

Regulatory TechnologyFinancial ServicesControlled Operational Environments

Tech Stack

Tools & technologies

AssemblyAWSCloudPython

About the role

Key responsibilities & impact

Build and operate production-grade AI systems using foundation models, retrieval, tool-use and workflow services for regulatory challenges
Own model and tool integration, retrieval and context assembly, provenance mechanisms, workflow orchestration, evaluation instrumentation and failure handling
Develop retrieval-augmented generation capabilities, including context and retrieval pipelines, semantic search, structured outputs, evidence references and citation verification
Design multi-step and agentic workflows with human review, approval, escalation and safe-failure mechanisms
Implement controls for known AI failure modes and appropriate operational monitoring
Build agentic orchestration covering planning and replanning, structured tool use, persistent state, semantic and episodic memory, agent hand-offs, execution limits, human interruption and recovery
Partner with stakeholders to create evaluation datasets and automated testing frameworks
Measure task success, retrieval quality, source support, robustness, latency, cost efficiency and regression performance
Build resilience against prompt injection, unsafe tool use, access-control failure, data leakage, unsupported claims, retrieval failures and model or configuration degradation
Collaborate with Platforms and Engineering, architecture, product and domain specialists across Authorisations, Supervision, Enforcement and AML
Contribute to CI/CD, release management, runtime operations, engineering quality, supplier oversight, knowledge transfer and organisational capability building

Requirements

What you’ll need

Solid Python and production software engineering, including APIs, automated testing and cloud-native services
Practical experience building and operating production applications using foundation models and LLM APIs
Experience with retrieval and embedding pipelines, semantic search or equivalent AI data pipelines
Experience with evaluation and monitoring of AI systems, including golden datasets, regression suites, retrieval assessment and citation quality measurement
Experience designing evidence-grounded, human-authorised workflows with explicit failure handling, abstention criteria and escalation pathways
Working knowledge of AI failure modes, including hallucination, retrieval drift, context failure, prompt injection and performance degradation, with appropriate controls
Experience implementing CI/CD, version control and operational telemetry
Secure engineering practices, including access control, data leakage prevention and safe tool usage
Ability to communicate technical trade-offs within multidisciplinary teams, review supplier deliverables and ensure knowledge transfer
AWS Bedrock and AgentCore or comparable cloud and foundation model platforms particularly valuable
Experience with agent orchestration, event-driven systems, graph-enhanced retrieval, and temporal and provenance models particularly valuable
Practical experience evaluating complete agent trajectories and memory behaviour particularly valuable
Delivery within regulatory technology, financial services or other controlled operational environments particularly valuable

Benefits

Comp & perks

25 days annual leave plus bank holidays
Minimum 50% of working time in the office each month
Non-contributory pension (8–12% depending on age)
Life assurance at eight times your salary
Private healthcare with Bupa
Income protection
24/7 Employee Assistance
35 hours of paid volunteering annually
Flexible benefits scheme
Flexible working solutions, including part-time and job sharing where applicable