FDE - AI

Forward Deployed Engineer: Agentic AI

OneByZero

Location: Singapore

Experience: 4 - 6 Years

About OneByZero

OneByZero is a Frontier Systems Integrator building agentic AI systems for leading banks,

telecommunications companies, insurers, and retailers across Asia Pacific. We work on high-impact

problems for institutions operating the financial and digital infrastructure of the region.

We operate exclusively on AWS and leverage partnership programmes that provide co-sell reach,

funded innovation opportunities, and delivery credibility across multiple markets. We value

individuals who are technically strong, delivery-focused, collaborative, and committed to solving

complex engineering challenges.

The Role

The Forward Deployed Engineer: Agentic AI designs, builds, and deploys production-grade

multi-agent systems within regulated enterprise environments.

This role is responsible for developing scalable AI applications, retrieval pipelines, orchestration

frameworks, APIs, observability tooling, and production infrastructure while working closely with

Architects, Delivery teams, and enterprise client stakeholders.

The role requires strong hands-on engineering capability, production delivery experience, and a

strong understanding of enterprise AI engineering practices.

At OBZ, all engineers are expected to use AI tools effectively in their daily work. AI assistants and

workflow automation tools are expected to improve engineering productivity, testing, debugging,

documentation, and delivery execution.

What You Will Do

● Design and deliver production-grade multi-agent systems using orchestration

frameworks such as LangGraph, LangChain, CrewAI, or equivalent technologies.

● Build and maintain end-to-end RAG pipelines including chunking strategies, embedding

evaluation, retrieval optimization, reranking, and hallucination evaluation.

● Develop prompt frameworks, role instructions, escalation flows, and guardrail

mechanisms for enterprise AI applications.

● Implement production-grade AI guardrails including PII redaction, input sanitization,

output validation, adversarial testing, and security controls.

● Design and deploy AI systems within in-region and in-VPC enterprise environments using

AWS services and regulated deployment architectures.

● Build and maintain FastAPI services, streaming APIs, authentication layers, React-based

interfaces, and enterprise integrations.

● Deploy and manage workloads on ECS, EKS, SageMaker, Bedrock, API Gateway, and

related AWS infrastructure services.

● Implement CI/CD pipelines, automated testing workflows, infrastructure automation,

observability tooling, and production monitoring frameworks.

● Define and execute testing strategies including unit testing, integration testing, retrieval

testing, adversarial testing, and evaluation frameworks.

● Contribute to architecture reviews, low-level designs, solution documentation, and

technical proposal responses.

● Lead technical workstreams within engagements and support junior engineering team

members through reviews, debugging, and technical guidance.

● Contribute reusable engineering assets including runbooks, prompt libraries, evaluation

frameworks, deployment templates, and tooling accelerators.

What We Are Looking For

● 4 - 6 years of experience in software engineering, AI engineering, cloud engineering, or

backend platform development.

● Strong Python engineering capability with experience building production-grade backend

systems.

● Hands-on experience building AI applications using LLM APIs, RAG systems, orchestration

frameworks, or multi-agent workflows.

● Experience with LangGraph, LangChain, CrewAI, or similar agentic AI orchestration

frameworks.

● Strong understanding of retrieval systems, embeddings, vector databases, reranking,

chunking strategies, and AI evaluation methodologies.

● Experience deploying applications on AWS using services such as Bedrock, SageMaker,