Role : Java Backend Engineer - AI / GenAI Platforms

Role : Java Backend Engineer (AI/GenAI-enabled product teams)

Experience : 5+ years

Domain : Payments / Financial Services (preferred, not mandatory)

About the Role :

We are building a cohesive AI engineering team embedded within a global payments leader's Services organisation, delivering customer-facing analytics, insights, and AI-driven products. We are looking for strong Java backend engineers who can build scalable, production-grade services that power conversational bots, multi-agent systems, and domain-specific AI agents.

You will own backend service development for AI-enabled products - designing robust APIs, integrating LLM and retrieval components, and ensuring the platform scales securely and reliably in a regulated payments environment. This is an engineering-first role focused on rapid, high-quality delivery and short time-to-market.

Key Responsibilities :

- Design, build, and maintain scalable Java backend services and microservices (Spring Boot / Spring Cloud) powering AI-enabled products.

- Develop and expose secure, well-documented REST APIs consumed by AI agents, conversational interfaces, and front-end product teams.

- Integrate backend services with LLM APIs, RAG pipelines, vector stores, and agentic/multi-agent workflows.

- Build resilient, high-throughput services with strong attention to performance, latency, observability, and fault tolerance.

- Implement enterprise-grade security, data protection, and compliance controls appropriate to a payments environment (PII handling, access control, audit).

- Collaborate closely with AI/ML engineers, data scientists, architects, and product teams within an integrated pod, contributing from day one.

- Participate in code reviews, architecture reviews, and CI/CD-driven delivery; uphold engineering quality and velocity standards.

Must-Have Skills :

- 5+ years of hands-on Java (8/11/17+) backend development.

- Deep experience with Spring Boot / Spring Framework and microservices architecture.

- Strong experience designing and building RESTful APIs and service integrations.

- Hands-on experience with Generative AI / LLM integration - building services against model APIs (OpenAI, Azure OpenAI, Bedrock), prompt handling, and orchestration.

- Practical experience with RAG pipelines and vector databases (e.g. FAISS, Pinecone, Qdrant, pgvector) and semantic search.

- Experience integrating backend services with agentic / multi-agent AI workflows or AI orchestration frameworks.

- Solid understanding of relational and/or NoSQL databases, SQL, and data modelling.

- Experience with cloud platforms (AWS / Azure / GCP), containerisation (Docker, Kubernetes), and CI/CD pipelines.

- Sound grasp of system design, scalability, security, and performance optimisation.

Good-to-Have :

- Awareness of LLM evaluation, guardrails, and Responsible AI practices (DeepEval, RAGAS, red teaming).

- Payments / BFSI domain experience (BASE24, ACI, ISO 8583, card/transaction systems) is a strong plus.

- Exposure to LLM fine-tuning, model evaluation, or MLOps practices.

- Polyglot exposure (e.g. Python alongside Java) is welcome.

What We're Looking For :

Engineers who can integrate seamlessly into an existing product team and contribute immediately - self-sufficient, quality-focused, and comfortable delivering to tight product timelines. We value people who combine strong core engineering fundamentals with curiosity about applied AI, and who take ownership of outcomes rather than tasks.