Software Engineer - Agentic AI and LLM Applications

We’re partnering with a leading global financial services organization that is investing heavily in AI-enabled products and agent-based workflows across the enterprise. They’re looking for a strong Software Engineer to join on a contract-to-hire basis, working remotely based in the US while aligned to EST hours. This role will sit at the intersection of software engineering, AI/LLMs, data and cloud infrastructure, helping design and deliver production-grade agentic applications that integrate with complex enterprise systems. What You’ll Be Doing You’ll work closely with engineering teams and business stakeholders to turn real-world use cases into scalable AI-enabled solutions. Backend & Agentic AI Engineering Build Python-based backend services and APIsDesign and implement agent orchestration, including supervisor and sub-agent patternsDevelop asynchronous, multi-step workflows across enterprise systemsBuild end-to-end LLM-enabled application featuresImplement prompt and context management, structured outputs and response validationApply strong engineering practices around testing, code quality and error handling Retrieval & Data Engineering Build retrieval pipelines for grounding and context enrichmentImplement vector search and similarity retrievalDevelop search and indexing capabilitiesWork with object storage for source content and embeddings Front-End & Enterprise Integration Integrate AI services into enterprise platforms through secure APIs and gatewaysSupport React-based front-end applicationsEnsure front-end experiences are effectively integrated with backend AI services and collaboration tools AWS & Production Delivery Deploy and operate services within AWSBuild secure and scalable cloud-native applicationsApply best practices across IAM, resiliency and availabilitySupport CI/CD pipelines and environment managementImplement observability including logging, metrics and tracing across workflows, model calls and integrations Stakeholder Engagement Work directly with business stakeholders to understand use casesTranslate requirements into practical technical designsCommunicate trade-offs around quality, cost, risk and delivery timelines What We’re Looking For We’re particularly interested in engineers with experience across: PythonProduction software/backend engineeringLLMs and Generative AI applicationsAgentic or multi-agent architecturesAPIs and enterprise integrationsRetrieval-Augmented Generation / retrieval-based systemsVector databases, search or indexingAWSCI/CD and cloud-native deploymentReact or experience collaborating with front-end teamsBuilding reliable, production-grade applications rather than purely experimental AI prototypes Location: Remote (must be US Based) Working Hours: Must be able to work closely with teams operating on EST Engagement: Contract-to-Hire Rate: c.$150p/h Experience within financial services, asset management or another complex enterprise environment would be beneficial but is not essential. This is an opportunity to work on genuinely production-focused agentic AI applications within a large-scale enterprise environment, with the potential to convert into a permanent position.