Generative AI Software Engineer

ITC Infotech; Kuala Lumpur; On-site; MYR 120,000 - 240,000; Full time

Job summary

ITC Infotech Malaysia is seeking a high-caliber Generative AI Software Engineer to architect, build, and deploy production-grade AI solutions and autonomous agentic systems. You will bridge foundational models and enterprise software, collaborating with product teams to translate complex challenges into scalable AI products.

The role requires deep skills in LangChain, LangGraph, and full-stack engineering (Python, Node.js/TypeScript, React) alongside cloud-native AWS infrastructure.

Qualifications

• 3+ years in professional software engineering with 1–2+ years in production GenAI/LLM apps.
• Proven design, development and deployment of AI-powered systems.
• Dual competency in Python (FastAPI) and TypeScript/Node.js with React frontends.

Responsibilities

• GenAI & Agentic Solution Architecture: design multi-agent workflows with LangGraph/LangChain.
• Implement protocol integrations to interface LLMs with microservices and databases.
• Build high-throughput RAG pipelines with vector databases (Pinecone, Atlas).
• Ensure reliability, governance, and scalable, secure microservices on AWS.
• Develop dashboards and UI using React/Next.js for real-time AI generation.

Skills

Generative AI concepts

Multi-Agent Systems

Full-Stack Engineering

Cloud-Native Architecture

Agile/Lean Methods

Education

Bachelor’s degree in Computer Science or related field

Tools

LangChain

LangGraph

Python (FastAPI)

Node.js/TypeScript

React

PostgreSQL

MongoDB

DynamoDB

Redis

AWS

Docker

Kubernetes

Job description

We are seeking a high-caliber Generative AI Software Engineer to architect, build, and deploy production-grade Artificial Intelligence solutions and autonomous agentic systems. In this role, you will bridge the gap between cutting-edge foundational models (LLMs) and resilient, scalable enterprise software.

You will work closely with cross-functional product teams, engineering leads, and business stakeholders to translate complex domain challenges into intelligent, production-ready AI products. The ideal candidate pairs deep technical competency in Agentic AI systems (LangChain, LangGraph, Multi-Agent Orchestration) with battle-tested Full-Stack Engineering (Node.js/TypeScript, Python, React) and modern cloud-native infrastructure (AWS, Docker, Microservices).

If you are passionate about pushing beyond basic prompt wrappers to design sophisticated multi-agent architectures, self-correcting agentic loops, and scalable RAG pipelines, this role is built for you.

Key Responsibilities:

GenAI & Agentic Solution Architecture

• Architect Multi-Agent Systems: Design, prototype, and productionize collaborative multi-agent workflows using frameworks such as LangGraph and LangChain, enabling autonomous agents to execute complex, multi-step business processes.
• Implement Protocol Integrations: Deploy modular frameworks like the Model Context Protocol (MCP) and tool-calling interfaces to seamlessly interface LLMs with internal microservices, enterprise databases, and third-party APIs.
• Build Advanced RAG Architectures: Engineer high-throughput Retrieval-Augmented Generation pipelines incorporating semantic search, hybrid retrieval, dense vector embeddings, dynamic re-ranking, and vector databases (e.g., Pinecone, MongoDB Atlas Vector Search).
• AI Reliability & Governance: Develop deterministic evaluation loops, guardrails, and self-critique mechanisms to mitigate hallucinations, manage context windows efficiently, control token expenditure, and guarantee brand/policy alignment.

Full-Stack & Microservices Software Engineering

• Enterprise API & Backend Development: Build performant, secure, and resilient microservices and RESTful/WebSocket APIs using Python (FastAPI) and Node.js/TypeScript.
• Modern Web Frontend Integration: Deliver intuitive, responsive user interfaces and interactive dashboards using React, Next.js, and modern CSS frameworks (TailwindCSS) to showcase real-time AI generation, human-in-the-loop validation, and streaming responses.
• Data Pipelines & Storage: Design and manage scalable schemas across relational and NoSQL/Vector databases, including PostgreSQL, MongoDB, DynamoDB, and Redis.
• Cloud Architecture (AWS): Deploy, monitor, and scale AI microservices on AWS leveraging services such as ECS, EKS, Lambda, S3, SQS/SNS, API Gateway, and CloudWatch.
• Containerization & CI/CD: Containerize microservices using Docker and orchestrate deployment via Kubernetes and automated CI/CD pipelines (GitHub Actions / Bitbucket Pipelines).
• Production Support & Incident Triage: Provide tier-3 production support, perform root-cause analysis on system failures or model drift, and maintain 99.9% platform availability.
• Rapid Prototyping to MVP: Utilize Agile and Lean engineering methodologies to rapidly deliver proofs-of-concept (POCs) and iterate to Minimum Viable Products (MVPs).
• Continuous Tech Scouting: Continuously evaluate emerging foundational models (OpenAI GPT-4/o-series, Google Gemini/Vertex AI, Anthropic Claude, open-weights models) and agentic frameworks for commercial viability.
• Technical Documentation & Code Quality: Author clear architectural decision records (ADRs), API specifications, and system runbooks while fostering rigorous peer code reviews.

Required Experience:

• Professional Background: 3+ years of professional software engineering experience, with at least 1–2+ years dedicated to developing and deploying Generative AI and LLM-powered applications in production environments.
• Demonstrated AI Portfolio: Tangible experience having designed, built, and shipped production AI systems, such as:
• Autonomous or semi-autonomous multi-agent workflows (LangGraph/LangChain).
• Production RAG search engines with vector databases.
• AI-powered assistants, interactive copilot chatbots, or automated content-generation platforms with human-in-the-loop controls.
• Full-Stack Proficiency: Strong dual-competency across Python (FastAPI) and TypeScript/Node.js, with proven ability to craft UI frontends in React.
• Cloud & Microservices: Hands-on experience deploying containerized workloads (Docker) on cloud platforms, preferably AWS.
• Education: Bachelor’s degree in Computer Science, Software Engineering, Information Technology, or equivalent practical industry experience.

Preferred / Value-Add Qualifications:

• Familiarity with enterprise agent standards such as Anthropic’s Model Context Protocol (MCP) or Google Agent Development Kit (ADK).
• Experience with Audio/Speech AI services (Speech-to-Text, Text-to-Speech, Whisper, Polly, ElevenLabs).
• Relevant AWS Certifications (e.g., AWS Certified Developer Associate, AWS Solutions Architect).
• Background in InsurTech, FinTech, Contact Center automation, or enterprise customer experience platforms.