Senior AI Engineer

IAPPS HEALTH GROUP PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

IAPPS HEALTH GROUP PTE. LTD. in Singapore seeks a Senior AI Engineer to lead design, development, evaluation, and deployment of advanced AI systems solving complex business problems.

The role blends software engineering with applied AI research, focusing on generative AI, agentic systems, retrieval, evaluation, and reliable production operations. You will translate ambiguous business needs into scalable AI solutions, make architectural decisions, and raise engineering standards across the team.

Qualifications

• 7+ years of professional software engineering with production systems ownership.
• ],
• job_responsibilities_description:[

Responsibilities

• Own end-to-end delivery of AI initiatives: problem framing, research, prototyping, architecture, implementation, evaluation, deployment, monitoring, and continuous improvement.
• Design and build production-grade generative AI and agentic systems, including multi-agent orchestration, tool/function calling, MCP-based integrations, RAG, hybrid/vector search, knowledge graphs, and structured agent workflows.
• Design rigorous evaluation frameworks for LLM and agent systems, including task-specific evals, regression tests, quality metrics, human review, guardrails, and failure analysis.
• Research emerging AI/ML methods, papers, models, frameworks, and architectural patterns; rapidly prototype promising approaches and convert validated findings into practical production improvements.
• Engineer retrieval and context systems: document ingestion/chunking, embeddings, vector stores, reranking, context budgeting, grounding, and knowledge-base design.
• Optimize agent/model behavior through prompt and system-prompt design, tool schemas, stopping conditions, tool-call limits, model selection/routing, and fine-tuning techniques where justified.
• Build and maintain robust AI platform infrastructure across cloud and/or hybrid environments using containers, Kubernetes, CI/CD, observability, and secure deployment practices.
• Partner directly with product, engineering, data, and business stakeholders to turn loosely defined requirements into clear technical scope, measurable success criteria, and deployable solutions.
• Mentor engineers, conduct architecture and code reviews, establish reusable patterns and engineering standards, and provide technical leadership on complex AI problems.
• Ensure AI systems meet high standards for security, privacy, reliability, explainability, responsible AI, cost efficiency, and operational resilience.

Skills

Leadership

Communication

Problem solving

Mentoring

Architecture

Stakeholder management

Education

Bachelor's or Master's in CS/AI/Data Science

Tools

Python

SQL

Docker

Kubernetes

AWS/Azure/GCP

LangChain

LangSmith

Vector databases

Job description

Job Description

Role SummaryWe are seeking a Senior AI Engineer to lead the design, development, evaluation, and production deployment of advanced AI systems that solve complex business problems. The role combines strong software engineering with applied AI research, with particular emphasis on generativeAI, agentic systems, retrieval, evaluation, and reliable production operations.The successful candidate will translate ambiguous business needs into scalableAI solutions, make sound architectural decisions, and raise engineering standards across the team.

Key Responsibilities

• Own end-to-end delivery of AI initiatives: problem framing, research, prototyping, architecture, implementation, evaluation, deployment, monitoring, and continuous improvement.
• Design and build production-grade generative AI and agentic systems, including multi-agent orchestration, tool/function calling, MCP-based integrations, RAG, hybrid/vector search, knowledge graphs, and structured agent workflows.
• Design rigorous evaluation frameworks for LLM and agent systems, including task-specific evals, regression tests, quality metrics, human review, guardrails, and failure analysis.
• Research emerging AI/ML methods, papers, models, frameworks, and architectural patterns; rapidly prototype promising approaches and convert validated findings into practical production improvements.
• Engineer retrieval and context systems: document ingestion/chunking, embeddings, vector stores, reranking, context budgeting, grounding, and knowledge-base design.
• Optimize agent/model behavior through prompt and system-prompt design, tool schemas, stopping conditions, tool-call limits, model selection/routing, and fine-tuning techniques where justified.
• Build and maintain robust AI platform infrastructure across cloud and/or hybrid environments using containers, Kubernetes, CI/CD, observability, and secure deployment practices.
• Partner directly with product, engineering, data, and business stakeholders to turn loosely defined requirements into clear technical scope, measurable success criteria, and deployable solutions.
• Mentor engineers, conduct architecture and code reviews, establish reusable patterns and engineering standards, and provide technical leadership on complex AI problems.
• Ensure AI systems meet high standards for security, privacy, reliability, explainability, responsible AI, cost efficiency, and operational resilience.

Must-Have Experience

• 7+ years of professional software engineering experience, including substantial ownership of production systems; typically 3+ years of hands-on AI/ML or modern AI engineering experience. Equivalent depth of experience is acceptable.
• Demonstrated experience shipping AI systems to production and owning them beyond prototype stage, including monitoring, incident handling, iteration, and adoption.
• Hands-on experience withLLM/GenAI application architecture such as RAG, agentic workflows, tool/function calling, MCP or comparable integration patterns, vector retrieval, and evaluation/guardrail systems.
• Strong Python and SQL skills, plus solid software engineering fundamentals in APIs, distributed systems, data structures, testing, version control, code review, and CI/CD.
• Production experience with cloud infrastructure (AWS, Azure, or GCP), Docker and Kubernetes, and relational/NoSQL data stores; practical experience with vector databases or vector extensions is strongly preferred.
• Ability to independently investigate unfamiliar technical problems, compare approaches experimentally, document findings, and make evidence-based architecture decisions.
• Experience working directly with non-technical stakeholders to clarify ambiguous requirements, explain trade-offs, and drive an AI solution from business problem through adoption.

Research & Applied AI Strength

• Strong research mindset: able to identify relevant papers, benchmarks, model releases, frameworks, and open-source implementations; distinguish novelty from practical value; and communicate implications clearly.
• Experimental discipline: formulate hypotheses, establish baselines, define measurable success criteria, run controlled experiments, analyse errors/failure modes, and preservere producible results.
• Ability to evaluate model and architecture choices across quality, latency, cost, security, maintainability, and operational complexity rather than optimizing a single metric.
• Comfort moving between research and engineering: build proofs of concept quickly, then harden successful approaches into tested, observable, maintainable production systems.

Technical Skills

• AI/GenAI: LLM application engineering, RAG, embeddings, vector and hybrid search, reranking, agent orchestration, MCP, tool/function calling, prompt/system-prompt engineering, context engineering, evals, guardrails, knowledge graphs, and fine-tuning approaches such as LoRA.
• ML foundations: machine learning/deep learning concepts, model evaluation and optimization; familiarity with PyTorch, TensorFlow, scikit-learn or equivalent frameworks.
• Data: Python, SQL,Pandas/NumPy; experience with PostgreSQL and/or other SQL/NoSQL databases; familiarity with data warehouses and large-scale data processing is advantageous.
• Platform: AWS/Azure/GCP,Docker, Kubernetes, micro services, CI/CD, monitoring/observability, secure secrets/configuration management, and scalable service design.
• AI tooling: hands-on experience with relevant orchestration/evaluation frameworks such as LangChain, LangGraph, LangSmith or comparable tools; ability to assess tools critically rather than depend on a single framework.

Leadership & Critical Skills

• High ownership and autonomy:can lead technically ambiguous work from first conversation to reliable production operation.
• Systems thinking: understand show models, prompts, retrieval, tools, data, infrastructure, security, user experience, and business processes interact as one system.
• Excellent debugging and root-cause analysis across application, model, retrieval, data, and infrastructure layers.
• Strong written and verbal communication, including architecture documentation, research summaries, technical proposals, and clear explanations for non-technical stakeholders.
• Mentoring and technical influence: improves team capability through reviews, reusable patterns, standards, and knowledge sharing.
• Pragmatic product judgement: balances sophistication with measurable business value, reliability, delivery speed, and total cost of ownership.

Education & Preferred Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field; equivalent demonstrable experience may be considered.
• Experience building AI platforms or reusable internal AI capabilities used across multiple teams or business functions.
• Experience with hybrid/on-prem and cloud estates, production Kubernetes, data/analytics agents, workflow automation, or enterprise integrations.
• Published research, technical writing, meaningful open-source contributions, benchmark/evaluation work, or other evidence of sustained AI research and experimentation is a strong advantage, but not mandatory.
• Experience with computer vision, NLP, reinforcement learning, speech, or classical ML is advantageous where relevant to business use cases.