AI Engineer

VentureSEA; Jakarta Pusat; On-site; IDR 300,000,000 - 600,000,000; Full time

Benefits offered by this job

null

Job summary

VentureSEA is seeking an AI Engineer to design, build, and deploy AI systems and agentic workflows powering internal employee-facing apps. You will architect LLM-powered capabilities, build RAG pipelines, and connect them to Microsoft 365 data sources via API integrations.

You will lead production deployments, optimize performance, ensure security, and collaborate with stakeholders to translate business problems into scalable AI solutions.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or related field.
• Minimum 3 years in software or AI/ML engineering or related role.
• Strong proficiency in Python for building AI systems and integrations.
• Experience deploying generative AI/LLM-based systems to production.
• Hands-on with agentic workflows, tool calls, and multi-step orchestration.
• Experience with LLM APIs and frameworks (Azure OpenAI, OpenAI, Anthropic, LangChain, LlamaIndex, LangGraph, Semantic Kernel).
• Experience building RAG pipelines with embeddings and vector search.
• Experience integrating REST APIs and enterprise data sources.
• Understanding of application security, data privacy in AI systems.
• Strong analytical skills and ability to work with non-technical stakeholders.

Responsibilities

• AI System Design & Development: build LLM-based systems for enterprise search and QA.
• Develop RAG pipelines: ingestion, embedding, indexing, retrieval, re-ranking.
• Design grounding strategies for accurate, source-traceable outputs.
• Apply prompt engineering and evaluation to improve quality.
• Model selection and architecture evaluation for cost and latency.
• Agentic Workflows & Automation: multi-step reasoning and tool use.
• Define tool-calling interfaces and safe action schemas.
• Implement orchestration: state, routing, retries, fallbacks, approvals.
• Security, Governance & Responsible AI: data privacy, safeguards, auditability.
• Production Deployment & Operations: versioning, monitoring, logging, CI/CD.
• Integrations: connect AI with Microsoft 365 data sources and expose APIs.
• Collaborate with frontend teams to embed AI features.

Skills

Python

Agentic workflows

LLM APIs

REST APIs

Production deployment

AI/ML engineering

Problem solving

Communication

Education

Bachelor's degree in Computer Science or related

Tools

Azure OpenAI

OpenAI

Anthropic

LangChain

LlamaIndex

LangGraph

Semantic Kernel

Job description

We are looking for an AI Engineer to design, build, and ship AI systems and agentic workflows that power a set of in-house employee-facing applications.

This role is centred on building AI capability — retrieval systems, LLM-powered reasoning, and multi-step agentic workflows — and connecting that capability into a Microsoft-native web environment. The successful candidate will take business problems from concept to production: designing the AI architecture, building the pipelines and agents, grounding them in enterprise data from Entra ID and SharePoint, and exposing them reliably to end users through APIs and application integration. This is an AI engineering role with strong integration responsibilities, not a general web development role.

Key Responsibilities

1. AI System Design & Development

Design and build LLM-based systems for enterprise search, question answering, summarization, and content generation.

Build retrieval-augmented generation (RAG) pipelines covering ingestion, chunking, embedding, indexing, retrieval, and re-ranking.

Design grounding strategies that keep outputs accurate, traceable, and anchored to authoritative internal sources.

Apply prompt engineering, structured output design, and systematic evaluation to improve quality and consistency.

Select and evaluate models, retrieval approaches, and architectures against cost, latency, and accuracy requirements.

2. Agentic Workflows & Automation

Design and implement agentic workflows capable of multi-step reasoning, tool use, and task completion.

Define and build tools, function-calling interfaces, and action schemas that allow agents to query systems and perform tasks safely.

Implement orchestration logic including state management, routing, retries, fallbacks, and termination conditions.

Build human-in-the-loop checkpoints and approval steps for actions with business or compliance impact.

Establish guardrails, boundaries, and failure handling so agent behaviour remains predictable and contained.

Integrate AI services with Microsoft 365 data sources — Microsoft Graph, Entra ID, SharePoint document libraries, and related services.

Build and expose APIs and services that allow web applications to consume AI capabilities.

Implement permission-aware retrieval so AI responses respect each user's existing access rights to underlying content.

Handle authentication and authorization flows (Entra ID / OAuth) between AI services, applications, and data sources.

Work with application developers to integrate AI features into the frontend experience.

4. Production Deployment & Operations

Deploy AI systems and agents to production with appropriate versioning, configuration management, and release controls.

Implement evaluation, monitoring, logging, and tracing across AI workflows — covering output quality, latency, cost, tool-call success, and failure modes.

Optimize token usage, caching, retrieval efficiency, and model selection to manage cost and performance at scale.

Diagnose and resolve production issues across the AI, integration, and data layers.

5. Security, Governance & Responsible AI

Apply secure handling practices for employee and corporate data, including PII minimization and secure secrets management.

Implement safeguards against prompt injection, tool misuse, data leakage, and unintended agent actions.

Maintain auditability of AI decisions and agent actions to support governance and compliance review.

Document architecture, data flows, prompts, tool definitions, evaluation results, and known limitations.

Provide technical guidance and knowledge transfer to engineering and support teams.

Requirements

Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related discipline.

Minimum 3 years of experience in software engineering, AI/ML engineering, or a closely related role.

Strong proficiency in Python for building AI systems, services, and integrations.

Demonstrated experience deploying generative AI or LLM-based systems to production, not solely prototypes or notebooks.

Hands-on experience building agentic workflows — tool use, function calling, multi-step orchestration.

Practical experience with LLM APIs and frameworks (e.g. Azure OpenAI, OpenAI, Anthropic, LangChain, LlamaIndex, LangGraph, Semantic Kernel).

Experience building RAG pipelines, including embeddings and vector search.

Experience integrating with REST APIs and working with structured and unstructured enterprise data.

Understanding of application security, authentication, and data privacy as applied to AI systems.

Strong analytical and problem-solving skills, with the ability to work from ambiguous business requirements.

Good communication skills and the ability to work with non-technical stakeholders.

Preferred Qualifications

Experience with the Microsoft ecosystem — Microsoft Graph API, SharePoint Online, Entra ID, Azure OpenAI, Azure AI Search, Azure Functions.

Experience with agent frameworks such as LangGraph, Semantic Kernel, AutoGen, or the Microsoft 365 Agents SDK / Copilot Studio.

Experience with vector databases (e.g. Azure AI Search, pgvector, Pinecone, Qdrant, Chroma).

Experience with LLM evaluation and observability tooling (e.g. LangSmith, Langfuse, Ragas, or equivalent).

Experience with cloud deployment (Azure preferred), containerization (Docker), and CI/CD pipelines.

Familiarity with Model Context Protocol (MCP) or similar tool-integration standards.

Exposure to enterprise search, knowledge management, or digital workplace projects.

Awareness of responsible AI frameworks, AI governance, or model risk management.

Relevant certifications in Azure AI, machine learning, or cloud engineering.