Principal: AI & Product Engineer - Kenya

JOB SUMMARY

Minimum Qualifications (Required)AI & LLM EngineeringStrong experience integrating LLMs into production systems.Hands-on prompt engineering, guardrails, and hallucination mitigation experience.Experience building cloud-native AI services.Enterprise Backend Engineering8+ years as a senior/principal engineer building large-scale enterprise systems.Deep experience with:Java/Spring BootREST APIs & microservicesKafka or RabbitMQAWS + Kubernetes + DockerPostgres or MySQLRedis + ElasticFintech /Payments Expertise (Required)Experience with:Deep understanding of the end to end payments processing workflows. Reconciliation flows.Merchant onboarding & KYB/KYC.Settlement & payouts.Exception handling.Payment methods across multiple channelsSecurity, Governance & ComplianceUnderstanding of:PCI DSS boundariesGDPR & data privacyAudit logging & traceabilitySensitive document handling.

RESPONSIBILITIES

Deliver AI Features for Reconciliation & Onboarding (Phase 1 Priority)Build semi-autonomous AI agents to automate reconciliation workflows, including:Payment method and bank reports/ statement ingestionTransaction matchingDiscrepancy analysisException explanation and routingReport generationDevelop AI-assisted KYB/KYC extraction tools to accelerate onboarding:Document parsing (IDs, certificates, statements).Entity extraction & validation.Risk flag identification.Build necessary API interfaces and Integrate AI services into existing/new microservices and event-driven pipelines.AI Engineering, LLM Integration & Agent OrchestrationIntegrate with multiple LLM providers through a hybrid model strategy (commercial APIs + open-source models).Implement prompt engineering, safety guardrails, and mechanisms to mitigate hallucinations during workflow execution.Build and integrate semi-autonomous agents using LangGraph or similar frameworks.Design high-quality APIs, SDKs, and internal tooling to allow product squads to embed AI seamlessly.Work with vector databases (PGVector, Pinecone, Weaviate—nice to have) for retrieval augmentation, semantic search, and agent memory.Cloud-Native & Enterprise Engineering ResponsibilitiesDeploy cloud-native AI services on AWS using Kubernetes, Docker, CI/CD pipelines, and secure infra patterns.Build scalable backend services using Spring Boot and event-driven flows via Kafka/RabbitMQ.Implement observability for AI systems (tracing, cost monitoring, latency, and prompt logs).Ensure strict compliance with:PCI DSS (tokenization boundaries, card-data safety).GDPR / data privacySensitive document handling for KYC/KYB and bank/payment method statements.Auditability and traceability for all AI outputsModel governance & safe operationsCross-Functional Collaboration & Product InfluencePartner with Product, Data Engineering, Finance Ops, Risk Ops, and Compliance to automate high-impact workflows.Translate complex business processes into AI-driven workflows with clear, measurable outcomes.Partner with Engineering and Platform teams to design, evolve and build out our next-gen payment architecture ensuring scalability, and AI integration ready design from the get go.Contribute (but not own) data ingestion pipelines needed for AI agents (PDF/CSV parsing, structured extraction e.t.c).AI Platform Evolution (Phase 2 Priority)After demonstrating initial business value:Design and lead the build-out of our internal AI Platform, including:AI gateway for model routingPrompt library & prompt evaluation toolingRetrieval pipelines & vector storesAgent orchestration frameworksEnterprise-grade governance and safety controls.Act as the founding member of a future AI Product Engineering team, likely taking on the technical leadership role of the team as the platform expands.Educate and coach internal squads on safe and effective use of AI tools.

REQUIRED SKILLS

Code documentation, Artificial intelligence (AI), Programming, Machine Learning (ML), Application programming interfaces (API)

REQUIRED EDUCATION

Diploma, Associate's degree