AI Engineer

SleekFlow; Hong Kong; Remote; HKD 600,000 - 900,000; Full time

Benefits offered by this job

13th-month salary

Stock options

International team culture

Birthday leave

Flexible work-from-home policy

Work From Anywhere scheme

Learning opportunities

More growth opportunities

Job summary

SleekFlow is hiring a Mid-Level LLM/RAG/Multi-Agent Infrastructure Engineer in Hong Kong to design, develop, and optimize AI infrastructure for integrating LLMs via APIs, and to build scalable RAG and multi-agent systems.

You will work at the intersection of AI apps, knowledge retrieval, and automation, collaborating with researchers and software teams to productionize models with strong observability, security, and compliance practices.

Qualifications

• Hands-on experience in integrating LLM APIs (OpenAI, Anthropic, Cohere) and building RAG pipelines with vector search.
• Familiarity with multi-agent systems and their infrastructure requirements.
• Experience in designing, indexing, and maintaining knowledge bases, including ontology design and embedding techniques.
• Experience with ML model versioning, deployment pipelines, and monitoring tools.
• Proficiency in designing structured prompts and using few-shot learning and chain-of-thought techniques.

Responsibilities

• LLM evaluation to select best models for applications.
• Develop and scale RAG architectures with vector databases and embedding models.
• Design infrastructure for multi-agent interactions and distributed decision-making.
• Build knowledge bases with domain data and automated indexing.
• Utilize vector/NoSQL databases and caching for AI workloads.
• Establish observability, logging, monitoring and tracing for APIs.
• Ensure data privacy, security, and compliance in deployments.
• Collaborate with researchers and engineers to deploy AI models.

Skills

LLM APIs & RAG

Multi-Agent Frameworks

Knowledge Base Engineering

CI/CD & MLOps

Prompt Engineering

Tools

FAISS

Weaviate

Pinecone

LangChain

AutoGen

CrewAI

Job description

SleekFlow is an AI Suite for Revenue-Driving Conversations. We are trusted by over 2,000 enterprises globally. But we are more than just a SaaS company; we are an AI-native movement redefining the B2C relationship across 70+ countries.

At our core is AgentFlow—an AI GTM workforce that learns, improves, and acts as a self-healing knowledge base for businesses. From first-click conversion to long-term retention, we turn every conversation into a data-backed growth opportunity. Headquartered in Singapore with a global presence in Hong Kong, the UAE, and the US, we are looking for exceptional people to help us build an AI operating system that matters.

Join us and rewrite how the world engages at scale.

Learn more from our blogs for developers: https://sleekflow.io/blog/category/developer-blog

Mid-Level

Location: Hong Kong

Minimum Experience: 1~2 years of experience working with RAG/LLM development and deployment

Language: Fluency in Chinese (Cantoness or Mandarin) and in English (reading & writing) is required, Fluency in English listening and speaking is preferable.

Role

We are seeking a highly skilled LLM/RAG/Multi-Agent Infrastructure Engineer to design, develop, and optimize infrastructure for integrating Large Language Models (LLMs) via APIs, building efficient Retrieval-Augmented Generation (RAG) systems, and enabling multi-agent frameworks. You will work at the intersection of AI applications, knowledge retrieval, and automation to create high-performance, scalable solutions that power next-generation AI-driven applications.

Key Responsibilities

• LLM Evaluation: Assess the strengths and limitations of various LLMs (e.g., OpenAI, Anthropic, Cohere) to determine the best fit for specific applications and use cases.
• RAG Pipeline Engineering: Develop and scale RAG architectures, integrating vector databases, retrieval mechanisms, and embedding models for efficient knowledge retrieval.
• Multi-Agent Coordination: Design robust infrastructure to support multi-agent interactions, enabling efficient message passing, distributed decision-making, and autonomous collaboration.
• Knowledge Base Development: Design and implement structured knowledge bases that enhance LLM output quality by integrating domain‑specific data, ontologies, and automated document indexing.
• Databases & Storage: Use vector databases, NoSQL databases, and caching mechanisms (e.g., Redis, PostgreSQL, ElasticSearch) to support efficient knowledge retrieval and AI workloads.
• Observability & Monitoring: Establish logging, monitoring, and tracing systems for API performance, system health, and anomaly detection.
• Security & Compliance: Ensure best practices for data privacy, security, and compliance in AI deployments.
• Collaboration: Work closely with AI researchers, ML engineers, and software developers to integrate AI models into production environments effectively.

Required Qualifications

• Experience with LLM APIs & RAG: Hands‑on experience in integrating LLM APIs (e.g., OpenAI, Anthropic, Cohere) and building RAG pipelines with vector search (e.g., FAISS, Weaviate, Pinecone).
• Multi-Agent Frameworks: Familiarity with multi-agent systems (e.g., LangChain, AutoGen, CrewAI) and their infrastructure requirements.
• Knowledge Base Engineering: Experience in designing, indexing, and maintaining structured and unstructured knowledge bases, including knowledge graph construction, ontology design, and text embedding techniques.
• CI/CD & MLOps: Experience with ML model versioning, deployment pipelines, and monitoring tools.
• Prompt Engineering Expertise: Proficiency in designing clear, structured prompts, optimizing AI responses through iterative refinement, and leveraging advanced techniques like few‑shot learning and chain‑of‑thought reasoning for improved accuracy and coherence.

Preferred Qualifications

• Prior experience in AI infrastructure for high‑traffic SaaS or enterprise AI applications.
• Knowledge of reinforcement learning and agent‑based AI systems.
• Experience with real‑time streaming architectures (Kafka, Ray, or similar).
• Experience in leveraging structured and semi‑structured data for improving LLM‑generated outputs.

Our Culture Code

• Open‑mindedness – We welcome different viewpoints and give and take feedback openly, always ready to challenge our own assumptions.
• Collaboration – We have each other's back, share knowledge freely, and treat every teammate with equal respect.
• Growth – We pursue continuous improvement, embrace new challenges, and treat mistakes as chances to learn.
• Ownership – We take initiative, see things through, and hold ourselves accountable for the outcome.
• Grit & Adaptability – We stay resilient through setbacks and adapt to change with patience and persistence.

What We Offer:

• Attractive compensation package, including a 13th-month salary.
• Stock options in a rapidly growing startup.
• A fun, diverse, and international team culture.
• Paid birthday leave.
• Flexible work‑from‑home policy.
• “Work From Anywhere” scheme.
• Rewarding continuous learning from experienced team leads.
• Many more exciting perks and growth opportunities!

Confidence can sometimes hold us back from applying for a job. But we'll let you in on a secret: there's no such thing as a 'perfect' candidate.