The role
We are looking for a Senior AI Systems Engineer to build and operate the intelligence layer of our AI products. This is a software-engineering-led role, not a prompt-development role: you will make model, retrieval, tool and orchestration behaviour testable, evidence-grounded, observable and reliable in production.
You will own the implementation of the product’s AI systems, including model integration, retrieval and context assembly, multi-step workflows, evaluation instrumentation, provenance mechanics and failure handling.
What success looks like
· AI outputs are grounded in data, and their supporting sources can be inspected wherever the risk tier requires it.
· Task, retrieval, citation and workflow quality are measured through repeatable evaluation and regression suites, with hooks exposed for independent evaluation.
· Prompts, models, orchestration logic, datasets, configurations and evaluation assets are versioned production artefacts.
· Known failure modes have explicit controls, abstention or escalation behaviour, and observable operational signals.
What you’ll do
· Design, build and operate foundation-model, retrieval and workflow services that solve the product’s operational problem.
· Build context and retrieval pipelines, structured outputs, evidence references and citation verification appropriate to the use case.
· Implement multi-step workflows with explicit human review, approval, escalation and safe-failure (abstention) paths.
· Work with stakeholders to create evaluation datasets and automated tests for task success, retrieval quality, source support, robustness, latency, cost and regression.
· Uphold security-conscious coding standards, building robustness against prompt injection, unsafe tool use, access-control failure, data leakage, unsupported claims, retrieval failure and model or configuration degradation, using appropriate third-party tooling.
· Work with Platform Engineering on CI/CD, release, runtime, observability and support, and with the Technical Lead on architecture and engineering quality.
· Review supplier code and artefacts, maintain documentation and ensure knowledge transfer into permanent FCA ownership.
What you’ll bring
Proven technical experience
· Strong 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, with a strong understanding of prompt engineering techniques and best practices.
· Experience with retrieval and embedding pipelines, semantic search or equivalent AI data pipelines.
Role-specific know-how, skills and behaviours
· Evaluation and monitoring of AI systems as a practice (golden datasets, regression suites, retrieval and citation quality measures, human and automated evaluation techniques) rather than ad hoc demonstration.
· Designing evidence-grounded, human-authorised workflows with explicit failure, abstention and escalation behaviour.
· Experience with data modelling, schema definition and validation frameworks.
· Working knowledge of AI failure modes (hallucination, retrieval drift, context failure, injection, degradation) and their controls.
· CI/CD, version control and operational telemetry, with prompts, configurations, datasets and evaluation assets treated as versioned production artefacts.
· Secure engineering: access control, data-leakage prevention and safe tool use.
· Communicating technical trade-offs within a multidisciplinary pod, reviewing supplier work and transferring knowledge.
· Translating non-technical business requirements from stakeholders into scalable, maintainable, robust solutions.
Particularly valuable
· AWS and Bedrock, or comparable cloud and foundation-model platforms.
· Extracting and structuring information from unstructured documents using OCR or multimodal foundation models.
· Agent orchestration, DAG orchestration, event-driven systems, graph-enhanced retrieval, or temporal and provenance models, including S3 metadata and annotation approaches.
· Regulatory technology, financial services or other controlled operational environments.
Why you’ll love this role
· Build production-grade AI systems that solve real regulatory problems, embedded in FCA operational workflows rather than standalone proofs of concept or demonstrations.
· Get hands-on experience at the forefront of enterprise AI engineering, including retrieval-augmented generation (RAG), agentic workflows, orchestration, evaluation frameworks, provenance, observability and secure AI system design.
· Help shape how a major financial regulator applies AI safely and responsibly, building systems that are evidence-grounded, measurable, auditable and designed to support meaningful human judgement.
· Tackle complex engineering challenges that go well beyond model integration, including retrieval quality, failure handling, evaluation, governance, security, operational resilience and long-term maintainability.
· Work alongside experienced engineers, architects, product leads and domain specialists while contributing to a growing AI capability intended to have impact across Authorisations, Supervision, Enforcement and AML activities.
À propos de Cognizant
Cognizant (NASDAQ : CTSH) est un AI Builder et une entreprise de services numériques (ESN) élaborant des solutions complètes d’IA maximisant les investissements pour des résultats concrets. Sa profonde expertise des métiers, des processus et des technologies lui permet d’intégrer dans les systèmes technologiques le contexte unique de chaque organisation de l’ingénierie à la production à l’échelle. Son objectif : améliorer l’efficacité des équipes, créer de la valeur et permettre aux grandes entreprises de rester performantes dans un monde qui évolue rapidement. Pour en savoir plus : cognizant.ai ou @cognizant.
Renseignments suppplémentaires sur l'emploi
Les informations relatives à la rémunération du poste à pourvoir dépendent de la date de publication de l’offre de poste. Cognizant se réserve le droit de modifier ces informations à tout moment, sous réserve des lois applicables.
Cognizant est un employeur soucieux de l'égalité des chances entre candidats. Votre candidature sera étudiée indépendamment de votre race, couleur, sexe, religion, croyances, orientation sexuelle, identité de genre, origine, handicap, informations génétiques, grossesse, statut d'ancien militaire ou de toute autre critère jugé discriminant par les lois européennes ou françaises.
Vous êtes porteur d'un handicap, vous pouvez-nous contacter par courriel [email protected] si vous souhaitez préciser les aménagements nécessaires pour le poste ou les entretiens à venir.
Les candidats peuvent être invités à participer à des entretiens en face à face ou par vidéoconférence. En outre, les candidats peuvent être amenés à présenter une carte d'identité valide lors de chaque entretien.
