AI Engineering Consultant

ABEAM CONSULTING (SINGAPORE) PTE. LTD.; Singapore; On-site; SGD 120,000 - 190,000; Full time

Job summary

ABeam Consulting (Singapore) PTE. LTD. seeks an experienced AI Engineer to design and deploy enterprise AI applications and agents. You will build LLM-based solutions using LangChain, MCP and related frameworks, and implement robust RAG pipelines across enterprise data sources.

You will collaborate with business users to translate requirements into scalable AI architectures, ensuring security, governance and observability for production-grade deployments.

Qualifications

• Hands-on experience in AI Engineering or Generative/Agentic AI development.
• Strong design of AI solutions using LLMs and RAG architectures.
• Proficient Python programming and API/backend development.

Responsibilities

• Identify, assess and prioritize AI use cases with stakeholders.
• Design, develop, test and deploy enterprise AI applications and agents.
• Build RAG pipelines including embedding, retrieval, and prompt engineering.
• Create multi-agent workflows with tool orchestration and memory management.
• Collaborate with security, data and architecture teams for production readiness.

Skills

Python

LLMs

LangChain

Agent orchestration

FastAPI

Tools

Azure OpenAI

FastAPI

Job description

About Us

ABeam Consulting is a global professional services company that specializes in delivering business transformation and technology solutions to clients across a wide range of industries. With a global presence and over 9000 employees worldwide we aim to be the transformation partner of choice for all of our clients.

Key Responsibilities

• Work with business users and stakeholders to identify, assess, and prioritize potential AI and Agentic AI use cases.
• Understand business processes, pain points, data availability, and system constraints, and translate them into appropriate AI solution designs.
• Design, develop, test, and deploy enterprise-grade AI applications and AI agents.
• Develop AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI frameworks.
• Design and implement single-agent and multi-agent workflows, including agent communication, task delegation, decision logic, memory, and tool orchestration.
• Develop orchestration workflows using technologies such as LangChain, LangGraph, MCP, and similar agent frameworks.
• Integrate AI agents with enterprise applications, databases, APIs, document repositories, and external tools.
• Develop robust backend services and APIs using Python and frameworks such as FastAPI.
• Design and implement RAG pipelines covering document ingestion, chunking, embedding, retrieval, hybrid search, reranking, prompt construction, and response generation.
• Build reusable AI components, agent tools, APIs, connectors, and services to accelerate future AI implementations.
• Develop POCs rapidly and work with stakeholders to validate business feasibility, technical feasibility, and expected value.
• Industrialize successful POCs into scalable and maintainable production solutions.
• Implement appropriate security, access control, guardrails, governance, observability, and monitoring for enterprise AI applications.
• Define evaluation frameworks and success metrics to assess AI agent performance, including response quality, accuracy, reliability, latency, token consumption, and business outcomes.
• Establish feedback loops and continuously improve AI agent performance based on evaluation results and user feedback.
• Troubleshoot and optimize AI applications, including prompts, retrieval quality, agent workflows, model selection, and system performance.
• Collaborate with infrastructure, security, application, data, and architecture teams to support successful enterprise deployment.
• Communicate AI concepts, solution architecture, limitations, risks, and recommendations clearly to both technical and non-technical stakeholders.
• Prepare solution documentation, architecture designs, implementation plans, technical specifications, test scenarios, and operational documentation.
• Provide knowledge transfer and technical guidance to client teams to support sustainable adoption of AI solutions.

Key Requirements

• Strong hands-on experience in AI Engineering, Generative AI, or Agentic AI development.
• Practical experience designing and implementing solutions using LLMs.
• Strong understanding of RAG architecture, including retrieval strategies, embeddings, vector search, hybrid search, reranking, and prompt engineering.
• Hands‑on experience with LangChain, LangGraph, or equivalent agent orchestration frameworks.
• Experience designing multi-agent workflows and tool‑calling/orchestration architectures.
• Strong programming skills in Python.
• Strong experience developing APIs, backend services, and integrations with enterprise applications.
• Experience developing AI solutions from POC through production deployment.
• Experience integrating AI solutions with structured and unstructured enterprise data sources.
• Understanding of AI application architecture, security, governance, access controls, guardrails, observability, and monitoring.
• Experience defining LLM/agent evaluation methodologies and performance metrics.
• Familiarity with cloud platforms and managed AI services, preferably Azure / Azure OpenAI.
• Experience and knowledge in Microsoft Copilot and Copilot Studio are mandatory; experience with Microsoft Foundry and Google Antigravity and Google Vertex AI are good to have.
• Strong analytical and problem‑solving capabilities.
• Ability to work independently and deliver solutions in a fast‑paced environment.
• Strong communication, stakeholder management, and consulting skills.
• Ability to work directly with business users to convert business requirements into practical AI solutions.

Preferred / Added Advantage

• Experience with MCP (Model Context Protocol) and agent tool integration.
• Experience with self-hosted or open-source LLM deployment.
• Experience with LLM evaluation frameworks such as DeepEval or equivalent.
• Experience with model fine-tuning, including SFT or other post-training techniques.
• Experience working with enterprise document-processing, OCR, knowledge-management, or search solutions.
• Familiarity with Azure, AWS, containerizatio