Artificial Intelligence Engineer

Position Overview:

We are seeking a Senior AI Engineer to design and build the core of our enterprise AI platform: production LLM applications, Retrieval-Augmented Generation (RAG/GraphRAG) systems, and agentic services that turn complex enterprise data into reliable, explainable answers.

This is a hands-on application-engineering role. You will own AI features end to end — from retrieval and orchestration through to streaming APIs and production reliability. You'll also lead applied R&D into self-hosted open models, benchmarking and selecting the right models for each task. A dedicated DevOps team owns production deployment, so your platform work is focused on evaluation and enablement, not running clusters.

Our platform is built in Python today and is evolving toward a microservices architecture; the stack will grow over time and may include additional languages and runtimes. We value engineers who reason from fundamentals and pick the right tool for the job rather than being tied to a single technology.

You'll work in a small, senior team building toward increasingly autonomous, agentic systems.

Location: UK or EU

Hybrid/Remote: Remote

Responsibilities:

AI Application Engineering (core)

· Design, build, and maintain production LLM-powered services: conversational agents, RAG/GraphRAG retrieval, and natural-language querying over enterprise data sources.

· Build and tune retrieval pipelines — combining semantic (vector) and keyword search, and knowledge-graph–backed context — for relevance and grounding.

· Implement agentic patterns: tool/function calling, multi-step reasoning, conversation memory, and real-time streaming responses.

· Engineer for reliability and explainability: guardrails/content safety, source attribution, evaluation, and graceful failure handling.

· Optimize latency, cost, and throughput across the LLM and embedding layers (caching, routing, token management).

Applied Model R&D & Self-Hosting

· Evaluate and benchmark LLMs and embedding models — both API-based and self-hosted.

· Stand up and assess self-hosted open models on modern serving runtimes, comparing quality, latency, and cost trade-offs.

· Drive model-selection decisions per task (chat, query generation, reranking, embeddings) and translate findings into production configuration.

Backend & Services Engineering

· Build high-quality, well-tested backend services and APIs (currently Python; the stack is evolving toward microservices and may span additional languages).

· Design durable, long-running workflows using a workflow-orchestration platform.

· Help shape the move toward a microservices architecture: clear service boundaries, contracts, and inter-service communication.

· Own the full lifecycle: requirements, design, implementation, testing, and production support.

· Maintain a clean, layered architecture and strong engineering standards.

Technical Leadership & Collaboration

· Provide technical direction and mentorship; lead design discussions for complex AI features.

· Partner with product, data, and DevOps teams to ship scalable solutions.

· Document architecture and decisions clearly for a distributed team.

Required Qualifications

· 8+ years of professional software engineering experience, with strong recent backend experience (Python preferred).

· Proven experience building production LLM / AI applications — RAG, agents, or similar — not just prototypes.

· Solid grasp of modern AI building blocks: embeddings, vector and hybrid search, prompt engineering, tool calling, and evaluation.

· Strong backend fundamentals: API design, asynchronous/concurrent programming, databases, and distributed-system architecture.

· Comfortable learning and adopting new languages, frameworks, and runtimes as the platform evolves.

· Working familiarity with containers and Kubernetes — enough to deploy, run, and debug model-serving workloads for evaluation (deep cluster operations are owned by DevOps).

· Experience leading technical initiatives and mentoring engineers.

· Comfortable in Agile, distributed teams.

Desired / Nice to Have

· Knowledge-graph–backed retrieval (GraphRAG) and graph databases

· Natural-language-to-SQL / structured-data querying over enterprise sources

· Self-hosting and serving of open LLMs on modern inference runtimes

· LLM routing / gateway layers across multiple providers

· Explainable AI and model evaluation framework

· Self-hosting and serving of open LLMs on modern inference runtimes

· LLM routing / gateway layers across multiple providers

· Explainable AI and model evaluation frameworks

· Vector databases and object storage

· Workflow-orchestration platforms for durable, long-running processes

· Microservices design and inter-service communication patterns

· Familiarity with GitOps / service-mesh environments (operated by DevOps — useful context, not a requirement)

· Observability and performance profiling

Preferred Experience

· Building AI features in an enterprise SaaS or platform-product organization.

· Working in AI/innovation-focused teams pushing toward agentic systems.

· Experience evolving a system toward microservices and/or polyglot stacks.

· Collaborating across international, distributed engineering teams.

Company Overview

At SBS, we’re more than just a technology company; we’re a global fintech partner helping banks and financial institutions transform, innovate, and grow. With over 5,000 employees worldwide and clients in more than 80 countries, our solutions power everything from digital banking and lending to payments and core banking systems.

As part of 74Software, we’re backed by a group of leading software companies delivering mission-critical solutions worldwide. Our focus is on delivering long-term value, leveraging cutting-edge technology, and fostering strong client partnerships. Join us and be part of a collaborative, forward-thinking team shaping the future of finance.

Why SBS?

At SBS, we’re committed to supporting our employees in every aspect of their lives, from health and wellbeing to financial security and lifestyle perks.

We offer benefits that help you thrive at work and beyond, including health coverage, retirement plans, paid time off, flexible work options, career development, competitive pay, and global culture perks.

Equal Opportunity Employer

We are committed to providing equal opportunities and ensuring a fair and inclusive recruitment process. We do not discriminate on the basis of age, disability, gender, sexual orientation, race, religion, or any other protected characteristic.