Technology support I in London

Description

Embark on a dynamic career in tech support, where your skills contribute to maintaining world-class technology solutions to ensure a seamless user experience.

As a Technology Support I team member in Commercial and Investment bank, you will ensure the operational stability, availability, and performance of our production application flows.

Be part of the team responsible for troubleshooting, maintaining, identifying, escalating, and resolving production service interruptions for all internally and externally developed systems, ensuring a seamless user experience.

• Job Responsibilities
• Troubleshoot and monitor production application flows to ensure end-to-end application or infrastructure service delivery to support business operations, addressing anomalies using standard observability tools.
• Uses enterprise-authorized AI capabilities within the work environment to speed up incident triage and initial problem analysis (e. g., summarizing logs/symptoms into hypotheses), validating outputs and handling operational data according to sensitivity and security requirements.
• Assist in the improvement of operational stability and availability through participation in problem management.
• Identify and document basic issues and potential solutions and support the management of incidents, problems, and changes in technology applications or infrastructure, escalating in compliance with firm policy and processes.
• Applies reuse-first, AI-assisted practices within operational stability routines to identify recurring interruption patterns and support validated remediation actions aligned to resiliency and security expectations.
• Execute creative LLM-assisted software solutions; design, develop, and troubleshoot LLM-powered applications and services (e. g., retrieval augmented generation, agent workflows, structured extraction, classification) with a willingness to think beyond routine approaches to break down technical problems and deliver measurable outcomes and think in the novel Agentic AI way.
• Provide Level 3 (L3) support for LLM-assisted production systems, own complex incidents, model and prompt rollouts/rollbacks, dependency issues (vector stores, embeddings, feature stores), and ensure high availability, reliability, and adherence to SLAs including latency and cost budgets.
• Develop data quality rules and controls using LLM; define and enforce guardrails for prompts, retrieved context, model inputs/outputs, and post-processing, including PII redaction, toxicity/safety filters, hallucination mitigation, output schema validation, and policy compliance.
• Create secure, high-quality production code: implement LLM-assisted microservices, synchronous and asynchronous inference pipelines (streaming where appropriate), deterministic fallbacks, circuit breakers, and observability for reliability in production.
• Produce architecture and design artifacts, deliver model cards, system/data lineage, RAG/agent reference architectures, prompt libraries and versioning strategies, evaluation plans, and control evidence ensuring design constraints and regulatory expectations are met during development.

Drive LLMOps best practices; integrate models, prompts, and evaluation into CI/CD, enforce approvals, segregation of duties, and reproducibility, automate regression and guardrail tests, and manage lifecycle across environments while ensuring LLM-driven systems meet enterprise reliability and resilience expectations (disaster recovery, fallback behaviors, regional resiliency, and performance SLOs).

• Required Qualifications, Capabilities, and Skills
• Formal training or certification on troubleshooting, resolving, and maintaining information technology services concepts and advanced applied experience
• Working knowledge of using enterprise-authorized AI capabilities within the work environment to support production support workflows with strong validation habits and awareness of data sensitivity.
• Ability to review and validate AI-assisted incident recommendations before action, escalating when uncertain and following operational and security expectations.
• Familiarity with applications or infrastructure in a large-scale technology environment on-premises or in the public cloud.
• Formal training or certification in software engineering concepts, with practical experience applying them to LLM-enabled systems in regulated environments.
• Strong coding skills in Java/Python and SQL, applied to building LLM-enabled microservices, retrieval pipelines, evaluators, and data tooling; solid understanding of data structures, algorithms, and object-oriented programming as applied to LLM latency, caching, and throughput.
• Hands-on experience with AWS and cloud data management (e. g., Redshift, Dynamo DB, Aurora, Databricks), plus experience integrating managed model endpoints and embedding/vector services; familiarity with secure secret management, networking, and least-privilege access.
• Proficiency in automation, CI/CD, and agile methodologies with LLMOps extensions: prompt and config versioning, automated evaluations, canary releases, and rollback strategies.
• Experience in system design, application development, and operational stability for LLM architectures, including retrieval layers, vector stores, caching, observability, rate limiting, and backpressure strategies.
• Strong analytical, problem-solving, and communication skills, including the ability to explain model behaviors, tradeoffs, and control decisions to both technical and non-technical stakeholders.

Strong understanding of how large language models work and of data-modeling challenges in big data and LLM contexts — embeddings, chunking strategies, vector similarity nuances, retrieval quality measures, and document lineage.

• Preferred Qualifications, Capabilities, and Skills
• Exposure to defining model-usage guidelines (which models fit requirements analysis, code generation/refactoring, test generation, and documentation) and to translating business and regulatory requirements into technical specifications, control implementations, and API/service contracts.
• Hands-on experience with modern application stacks and API tooling — e. g.,

Node/Express, React, REST API design and integration, and API testing with Postman/Insomnia

— applied to building LLM-assisted microservices and internal tooling.

• Familiarity with treating prompts and system instructions as versioned, reviewable engineering artifacts (change control, traceability) and with evaluation discipline — defining accuracy/performance benchmarks, seeded examples, output schemas, and canonical evaluation sets to support determinism and reproducibility.
• Working knowledge of secure-by-design and observability practices — authentication/authorization (Auth O, JWT, Bcrypt), ACL, CORS and least-privilege access, log analysis and monitoring (e. g., Grafana/Datadog/Splunk), and multi-cloud deployment (AWS Amplify/EC2/RDS, GCP)

— supporting guardrails, resiliency, and reliable production operations.

• Ability to continuously learn about new developments in Agentic AI and LLM-driven software coding, with demonstrated breadth across AI/ML domains (e. g., computer vision, structured data extraction, plugin/extensibility architectures, and third-party/market-data API integration such as Bloomberg ).