Location
Hybrid (Bangkok, Thailand)
Seniority
Middle · 4+ years exp
Employment
Full-Time
First seen by Alion on Oct 3, 2026.
Overview
Company
Impact
Profile match
Cube SoftTech is a software development and IT consulting company specializing in custom software solutions, mobile application development, and system integration. Headquartered in Bangkok, Thailand, the firm delivers end-to-end digital transformation services, workflow automation, and IT staff outsourcing. By partnering with enterprise clients across finance, telecommunications, and other major industries, the organization helps businesses modernize their technical infrastructure and optimize operational efficiency.
Description: Bangkok, Thailand (Hybrid).
Full-time.
Workplace: hybrid.
Department: Data, Product & Technology.
As one of our early AI Engineering hires, you'll help define what AI at Cube looks like. You'll build the AI features people actually use from our self-hosted chat interface and MCP server to retrieval pipelines, prompts, evaluations, and integrations with internal systems. You'll work closely with our Infrastructure and Data Engineering teams to design architecture, connect systems, and transform emerging AI capabilities into practical products and tools that solve real problems every day.
Maintain and tunning our self-hosted chat interface including model connections, MCP integration, RAG/knowledge base setup.
Build the RAG pipeline: ingestion, chunking, embeddings, vector store, retrieval, reranking, and evaluation.
Integrate LiteLLM or OpenRouter as the gateway; handle routing, fallbacks, rate limits, and cost tracking.
Maintain and configure MCP server and the tools it exposes to the model.
Write prompts and evaluations, and iterate on them based on real usage and failure cases.
Monitoring the logging, tracing, and guardrails of our AI platforms and model does.
Good to have exposure on MLOps/Platform team to deploy self-hosted models (vLLM, TGI, Ollama) and keep them healthy.
Ship features end-to-end: API, retrieval, prompt, evaluation, and rollout.
4+ years of software engineering experience.
Familiarity with containerized technologies and orchestration platforms such as Kubernetes.
Strong interest in AI, LLMs, and the rapidly evolving model ecosystem.
1+ years of experience building, deploying, or supporting production LLM systems (RAG, agents, or fine-tuned models).
Experience deploying and configuring self-hosted LLM chat interfaces (Open WebUI preferred; similar platforms are acceptable).
Hands-on experience with retrieval and RAG systems, including embeddings, vector databases, chunking strategies, hybrid search, and evaluation methodologies.
Experience working with LLM gateways or routing layers such as LiteLLM, OpenRouter, Portkey, or similar solutions.
Experience serving open-weight models using tools such as vLLM, TGI, or SGLang.
Experience designing and implementing secure integrations between LLMs and internal business systems.
Nice to have: Experience with or understanding of MCP servers, agent frameworks, or tool-calling architectures.
Nice to have: Experience with or understanding of LLM observability and monitoring platforms such as LangSmith, Langfuse, or similar tools.
Apply.
Apply at Cube](https://apply.workable.com/cube-asia/j/B70DBB4314/apply).
Job skills required: Architecture, Kubernetes
Full-time.
Workplace: hybrid.
Department: Data, Product & Technology.
As one of our early AI Engineering hires, you'll help define what AI at Cube looks like. You'll build the AI features people actually use from our self-hosted chat interface and MCP server to retrieval pipelines, prompts, evaluations, and integrations with internal systems. You'll work closely with our Infrastructure and Data Engineering teams to design architecture, connect systems, and transform emerging AI capabilities into practical products and tools that solve real problems every day.
Maintain and tunning our self-hosted chat interface including model connections, MCP integration, RAG/knowledge base setup.
Build the RAG pipeline: ingestion, chunking, embeddings, vector store, retrieval, reranking, and evaluation.
Integrate LiteLLM or OpenRouter as the gateway; handle routing, fallbacks, rate limits, and cost tracking.
Maintain and configure MCP server and the tools it exposes to the model.
Write prompts and evaluations, and iterate on them based on real usage and failure cases.
Monitoring the logging, tracing, and guardrails of our AI platforms and model does.
Good to have exposure on MLOps/Platform team to deploy self-hosted models (vLLM, TGI, Ollama) and keep them healthy.
Ship features end-to-end: API, retrieval, prompt, evaluation, and rollout.
4+ years of software engineering experience.
Familiarity with containerized technologies and orchestration platforms such as Kubernetes.
Strong interest in AI, LLMs, and the rapidly evolving model ecosystem.
1+ years of experience building, deploying, or supporting production LLM systems (RAG, agents, or fine-tuned models).
Experience deploying and configuring self-hosted LLM chat interfaces (Open WebUI preferred; similar platforms are acceptable).
Hands-on experience with retrieval and RAG systems, including embeddings, vector databases, chunking strategies, hybrid search, and evaluation methodologies.
Experience working with LLM gateways or routing layers such as LiteLLM, OpenRouter, Portkey, or similar solutions.
Experience serving open-weight models using tools such as vLLM, TGI, or SGLang.
Experience designing and implementing secure integrations between LLMs and internal business systems.
Nice to have: Experience with or understanding of MCP servers, agent frameworks, or tool-calling architectures.
Nice to have: Experience with or understanding of LLM observability and monitoring platforms such as LangSmith, Langfuse, or similar tools.
Apply.
Apply at Cube](https://apply.workable.com/cube-asia/j/B70DBB4314/apply).
Job skills required: Architecture, Kubernetes
Free account
Stop reading job ads. Get the ones that fit.
One free account turns this page into a shortlist built around your stack, your level and your pay.
Match on every job. Stack, seniority, pay and location, scored against your profile.
2,455,751 open roles. Read straight off company career pages, refreshed every day.
Unlimited applications. Every one you send is tracked in one place, on-site or on a company board.
3 tailored CVs a month. Rewritten for the exact job you are applying to. Included free.
Free forever. No card. Under a minute.
Your match
How well do you fit this role?
Two answers are enough for a real match. No account needed.
Check my fit
Answers stay in this browser until you create an account.
Recommended for you based on this role
AI/ML
Similar stack
Same company
Bangkok
Hybrid · Full-Time · 10+ years exp · Bachelor's Degree · Hyderabad
Databases
Databricks
Google BigQuery
Amazon Redshift
AI/ML
Vertex AI
Prompt Engineering
AI Agents
RAG
Amazon SageMaker
Human-in-the-Loop
Semantic Search
Knowledge Graph
LLM Guardrails
Multi-Agent Systems
Machine Learning
DevOps
GCP
CI/CD
Git
AWS
Kubernetes
Amazon EKS
Google GKE
Google Cloud Run
AWS Lambda
Amazon S3
IAM
Amazon ECS
Amazon CloudWatch
Apply
AI・マッチングエンジニア(正社員)
1 day ago
$38k – $57k per year · In office · Full-Time · Tokyo
JavaScript
TypeScript
Databases
PostgreSQL
Supabase
AI/ML
Claude
RAG
Frontend
Next.js
React.js
DevOps
Vercel
Apply
Postdoctoral Researcher
1 year ago
In office · Full-Time · PhD · United States
Python
C++
Robotics
Digital Twin
Apply
In office · Full-Time · Zurich
C++
AI/ML
Machine Learning
Apply
$180k – $275k per year · In office · 7+ years exp · PhD · Reston
C++
AI/ML
PyTorch
Machine Learning
DevOps
Wi-Fi
Apply
Senior Engineer - ML Operations
21 days ago
$180k – $220k per year · Remote (United States) · Full-Time · 4+ years exp · Bachelor's Degree · Washington
Python
AI/ML
LangGraph
Weights & Biases
LangChain
Claude
Model Context Protocol
vLLM
MLFlow
Prefect
Quantization
Function Calling
AI Agents
Langfuse
LiteLLM
TGI
LLM
RAG
CUDA
Triton
LLMOps
OpenAI Agents SDK
LLM Guardrails
Agentic Workflows
Multi-Agent Systems
Machine Learning
DevOps
OpenTelemetry
Azure
CI/CD
Docker
Kubernetes
Cybersecurity
HIPAA
Apply
Senior MLOps Engineer
21 days ago
≈ $119k – $230k per year (Estimated) · Hybrid · 10+ years exp · Bachelor's Degree · Plano
Python
Python
FastAPI
Databases
Databricks
Delta Lake
AI/ML
vLLM
Fine-tuning
RAG
RAPIDS
CUDA
Context Engineering
Knowledge Graph
Machine Learning
DevOps
Azure
CI/CD
Docker
Kubernetes
Azure AKS
Apply
Senior MLOps Engineer
21 days ago
$130k – $185k per year · Hybrid · 10+ years exp · Bachelor's Degree · Camas
Python
Python
FastAPI
Databases
Databricks
Delta Lake
AI/ML
vLLM
Fine-tuning
RAG
RAPIDS
CUDA
Context Engineering
Knowledge Graph
Machine Learning
DevOps
Azure
CI/CD
Docker
Kubernetes
Azure AKS
Apply
Senior/Staff Software Engineer - Tech Lead
21 days ago
$125k – $258k per year · Remote (United States, ET hours) · Full-Time
Python
Rust
TypeScript
Python
FastAPI
Rust
Tauri
AI/ML
Cursor
Claude Code
AI Agents
LLM
RAG
Agentic Workflows
DevOps
CI/CD
Apply
Senior/Staff Software Engineer - Tech Lead
21 days ago
$126k – $188k per year · Remote (Canada) · Contractor
Python
Rust
TypeScript
Python
FastAPI
Rust
Tauri
AI/ML
Cursor
Claude Code
AI Agents
LLM
RAG
Agentic Workflows
DevOps
CI/CD
Apply
Apply
QA Tester - Platform & Dashboards
1 month ago
Hybrid · Full-Time · 2+ years exp · Bangkok
SQL
Analytics
Tableau
Power BI
Looker
Apply
≈ $15k – $33k per year (Estimated) · Hybrid · Full-Time · 4+ years exp · Bangkok
JavaScript
TypeScript
SQL
Node JS
Databases
Snowflake
Frontend
Next.js
React.js
DevOps
GCP
Azure
AWS
Kubernetes
Apply
Data Engineer Specialist
1 day ago
In office · Full-Time · 3+ years exp · Bachelor's Degree · Bangkok
Python
SQL
Databases
Databricks
Apache Kafka
Analytics
ETL/ELT
Apply
EHS Managing Consultant
1 day ago
≈ $13k – $28k per year (Estimated) · In office · Full-Time · 8+ years exp · Bachelor's Degree · Bangkok
Apply
Apply
Remote (Malaysia, Thailand, Singapore) · Full-Time · 7+ years exp · Bachelor's Degree · Bangkok
DevOps
Incident Management
Life Sciences
GMP
Apply
Remote (Thailand) · Full-Time · 6+ years exp · Bachelor's Degree · Bangkok · Kuala Lumpur
Apply
This is one of many
2,455,751 more open roles from verified company boards, updated every day.

