AI Engineer

Thoughtfull-World; Kuala Lumpur; Presencial; MYR 93.000 - 148.000; Jornada completa

Descripción de la vacante

ThoughtFull, a Temasek-backed mental health company, seeks a seasoned software engineer to design, develop and deploy scalable AI applications based on LLMs. You will build AI agents, RAG pipelines, and backend services that integrate with OpenAI, Anthropic, and AWS Bedrock to deliver production-grade solutions.

Collaborating with product, engineering and clinical teams, you will optimize performance, latency and cost, implement guardrails, and advance responsible AI practices in a fast-growing

Formación

• Degree in Computer Science, Engineering, or a related field.
• 4+ years of professional software engineering experience, including AI/LLM applications.
• Strong proficiency in Python and backend frameworks such as FastAPI or Django.
• Hands-on experience integrating LLM APIs (OpenAI, Anthropic, or similar).
• Experience building production-grade LLM applications using prompting, structured outputs, and tool calling.
• Familiarity with AI agents and agentic workflows (LangGraph, LangChain).
• Knowledge of RAG architectures, embeddings, and vector databases (e.g., Pinecone, Milvus).
• Understanding AI evaluation, testing, and prompt-injection risks.
• Experience with AWS, Docker, and cloud infrastructure.
• CI/CD, Git, and monitoring familiarity.
• Security, privacy, and responsible AI practices.

Responsabilidades

• Design, develop, and deploy scalable AI applications using LLMs and modern frameworks.
• Build AI agents and automated workflows integrating with APIs, databases, tools, and systems.
• Develop and optimize RAG pipelines including embeddings, vector search, and retrieval strategies.
• Integrate LLM providers like OpenAI, Anthropic, and AWS Bedrock with prompting and function calling.
• Develop and maintain backend services and RESTful APIs for AI-powered apps.
• Implement AI evaluation frameworks and guardrails to ensure accuracy, safety, and privacy.
• Optimize AI application performance, latency, token usage, and costs.
• Deploy, monitor, and maintain AI services using cloud infra, Docker, and CI/CD.
• Collaborate with product, engineering and clinical teams to translate requirements into AI solutions.
• Research and evaluate emerging AI technologies to improve capabilities.

Conocimientos

Python

Backend development

AI/LLM applications

RESTful APIs

Problem solving

Educación

Bachelor's degree in Computer Science or related field

Herramientas

OpenAI API

Anthropic API

AWS Bedrock

Docker

LangChain

LangGraph

Pinecone

Milvus

pgvector

Descripción del empleo

About ThoughtFull

ThoughtFull is on a mission to simplify mental health for your personal and professional growth - through every season of life, anytime, anywhere.

ThoughtFull is a Temasek-backed mental health company that provides full mental healthcare services for corporates clients around the Asian region and beyond. We were the first in Asia to offer clinically validated text-based coaching and the first to partner with insurers, making care more accessible to individuals and businesses. Join us on our mission and be part of our rockstar team!

What you will do:

• Design, develop, and deploy scalable, secure, and production-ready AI applications using Large Language Models (LLMs) and modern AI frameworks.
• Build AI agents and automated workflows that integrate with APIs, databases, tools, and existing systems to enhance product capabilities and operational efficiency.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, including document processing, embeddings, vector search, and retrieval strategies.
• Integrate and manage LLM providers such as OpenAI, Anthropic, and AWS Bedrock, utilizing prompt engineering, structured outputs, and function calling.
• Develop and maintain backend services and RESTful APIs to support AI-powered applications and integrations.
• Implement AI evaluation frameworks and guardrails to ensure accuracy, consistency, safety, reliability, and protection of sensitive data, including appropriate human escalation mechanisms.
• Optimize AI application performance, response latency, token usage, and infrastructure costs.
• Deploy, monitor, and maintain AI services using cloud infrastructure, Docker, and CI/CD pipelines.
• Collaborate with product, engineering, and clinical teams to translate business requirements into effective AI‑powered solutions.
• Research and evaluate emerging AI technologies, models, and frameworks to continuously improve AI capabilities and engineering practices.

About you

Skills and Qualifications:

• Degree in Computer Science, Engineering, or a related field
• 4+ years of professional software engineering experience, including practical experience building AI/LLM applications.
• Strong proficiency in Python and backend development frameworks such as FastAPI or Django.
• Hands‑on experience integrating LLM APIs, including OpenAI, Anthropic, or similar providers.
• Experience building production‑oriented LLM applications using prompting, structured outputs, and tool/function calling.
• Practical experience with AI agents and agentic workflows, including frameworks such as LangGraph, LangChain, or equivalent approaches.
• Solid understanding of RAG architectures, embeddings, retrieval techniques, and vector databases such as pgvctor, Pinecone, Milvus, or similar.
• Understanding AI evaluation, automated testing, hallucination mitigation, and prompt‑injection risks.
• Experience with agentic AI architectures, agent harnesses, and iterative execution loops, including tool orchestration, feedback loops, state management, and automated
• Experience designing RESTful APIs, integrating databases, and developing backend services.
• Hands‑on experience with AWS, Docker, and cloud infrastructure.
• Familiarity with CI/CD pipelines, Git, and application monitoring.
• Knowledge of application security, data privacy, and responsible AI development.
• Strong problem‑solving skills and the ability to independently deliver AI features from prototype to production.

Preferred Qualifications:

• Experience with AWS Bedrock and cloud‑native AI services.
• Experience implementing multi‑agent systems and AI workflow orchestration.
• Familiarity with LLM observability, tracing, and evaluation tools such as LangSmith, Langfuse, or similar.
• validation.
• Experience with speech‑to‑text, real‑time conversational AI, or voice agents.
• Understanding of model fine‑tuning, model selection, and inference optimization.
• Knowledge of machine learning fundamentals, NLP, and transformer‑based architectures.
• Experience working with sensitive healthcare data or regulated environments.
• Experience developing AI solutions for healthcare, mental health, or personalized recommendation systems.

IMPORTANT NOTE:

• Time Zone: Must be able to work in Malaysia/Singapore time (GMT+8).
• Language: Must be proficient in English, with strong written and verbal communication skills.
• Unfortunately, we're not able to offer visa sponsorship at this time.

Basic Salary Range: MYR8,300 - MYR13,300

Thoughtfull is an equal opportunity employer. We provide equal employment opportunities regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. If you have a disability or special need, please inform us for accommodation.