Our client, a technology consultancy specialising in cloud, data, and AI-driven solutions for enterprise customers, is expanding its engineering team. This role sits at the intersection of traditional full stack development and applied AI — building products that incorporate agentic workflows and LLM-powered capabilities, engineered to production standards of reliability and scale.
The successful candidate will contribute across the full software lifecycle, from system design and implementation through to operational ownership of AI-powered services in production.
Key Responsibilities
Software Engineering
- Develop and maintain full stack applications using Python, JavaScript/TypeScript, and Go
- Design scalable system architecture, including service boundaries, caching, queuing, and failure handling
- Design efficient database schemas and queries
- Define and document API contracts (REST, gRPC, or GraphQL) for internal and external consumers
- Containerise and deploy services using Docker and Kubernetes
Applied AI & Agentic Systems
- Design and implement agentic AI workflows, including multi-step task execution, tool use, memory, and multi-agent orchestration
- Integrate large language models, third-party AI APIs, and internal data sources into production systems
AI Operations
- Build and maintain operational pipelines for LLM-based systems, covering deployment, monitoring, evaluation, prompt and model versioning, and cost tracking
- Own the reliability and performance of production systems, including monitoring, alerting, and incident response
Collaboration & Governance
- Work closely with product, research, and engineering stakeholders across the SDLC
- Participate in code reviews, architecture discussions, and technical planning
- Contribute to technical documentation and runbooks to support long-term maintainability
Candidate Requirements
- 2–6 years of professional experience building full stack applications, backend services, and production-grade software systems
- Strong working proficiency in Python and JavaScript/TypeScript
- Working knowledge of Go, or demonstrated ability to acquire it quickly
- Practical experience with infrastructure-as-code tools such as Terraform (Ansible advantageous)
- Experience with cloud and/or on-premise infrastructure
- Proficiency with Docker; working knowledge of Kubernetes advantageous
- Demonstrated experience building or operating AI-powered systems, agentic workflows, or LLM-based applications
- Familiarity with agent orchestration principles — multi-step reasoning, tool use, memory, multi-agent design
- Working knowledge of MLOps/AIOps practices, including model or prompt versioning, evaluation pipelines, and observability
- Solid understanding of system design fundamentals, including scalability, reliability, and distributed systems trade-offs
- Strong communication skills and a demonstrated sense of technical ownership
Advantageous
- Direct experience with LLM providers such as OpenAI, Anthropic, or Azure OpenAI, or with open-source models
- Experience with RAG, embeddings, or vector databases
- Understanding of security principles applicable to both traditional and AI systems
- Prior experience within a startup or applied AI product environment
What the Role Offers
- The opportunity to build production-grade products combining software engineering with applied AI
- Exposure to agentic AI systems and LLM-powered infrastructure at scale
- A flat, low-bureaucracy team structure that supports rapid execution
- Close collaboration with product, research, and engineering functions from concept through to deployment
- Structured learning and development support, including courses and conferences
- Competitive remuneration and benefits
ST
Reg No. R1768414
BeathChapman Pte Ltd
Licence no. 16S8112
