Job Title: AI Engineer 

Location: Manila, Metro Manila, Philippines

Job Type: Remote

About the Opportunity

Our client is expanding their Data & AI team and is seeking an experienced AI Engineer to design and build next-generation enterprise solutions. This role focuses on developing LLM-powered chatbots, advanced search systems, and automation tools.

This is a highly technical position that also involves client-facing elements. It is ideal for an engineer who enjoys solving real-world business problems by applying cutting-edge AI tools, frameworks, and the Google Cloud technology stack. You will play a key role in orchestrating workflows and building intelligent conversational interfaces.

Key Responsibilities

• LLM Application Development: Design, develop, and optimize advanced AI chatbots and applications using Large Language Models (LLMs) such as Gemini, LLaMA, and Claude.
• RAG & Search: Build semantic and enterprise search systems powered by RAG (Retrieval-Augmented Generation) pipelines and vector databases.
• Orchestration: Architect and orchestrate complex LLM workflows using LangChain and LangGraph.
• Backend Engineering: Develop robust backend services and REST APIs using FastAPI to support AI-powered applications.
• Prototyping: Build interactive AI dashboards and demonstration tools using Streamlit for rapid prototyping and client presentations.
• Model Optimization: Implement prompt engineering, model tuning, and evaluation strategies tailored to specific business domains. Fine-tune foundation models and implement domain-specific customizations.
• Cloud Integration: Integrate and deploy scalable solutions leveraging the Google Cloud ecosystem, including Vertex AI, Document AI, Dialogflow CX, BigQuery, and Cloud Functions.
• Engineering Best Practices: Contribute to the engineering culture by maintaining high standards for documentation, CI/CD pipelines, and code reviews.
• Collaboration: Collaborate closely with Data Engineers and Solution Architects to deliver scalable, production-ready AI systems.

Essential Skills & Experience

• Experience: 3+ years of professional experience as an AI/ML Engineer or Software Engineer with a focus on AI projects.
• Core AI Knowledge: Strong understanding of LLMs, transformers, and conversational AI architectures.
• Orchestration Frameworks: Proven experience with LangChain or LangGraph.
• Development Stack: Hands-on experience with FastAPI (or Flask) for backend development and Streamlit for tooling/demos.
• Vector Search: Proficient in vector search, embeddings, and similarity-based retrieval tools (e.g., FAISS, Weaviate, Pinecone, Milvus).
• GCP Stack: Working knowledge of Google Cloud Vertex AI, Document AI, and Dialogflow CX.
• Methodologies: Familiarity with Prompt Engineering, RAG pipelines, and LLM evaluation methodologies.
• Software Engineering: Strong foundation in Git, CI/CD, and testing protocols.

Preferred Skills (Nice-to-Have)

• Data Engineering: Experience with ETL tools, Airflow, dbt, BigQuery, or Snowflake.
• LLM Fine-Tuning: Experience fine-tuning open-source LLMs (e.g., LLaMA, Mistral, Falcon).
• Optimization: Understanding of LLM safety, reliability, and cost-performance optimization.
• Infrastructure: Familiarity with cloud infrastructure on GCP, AWS, or Azure.
• Frontend: Exposure to frontend frameworks like React or Next.js.

How to Apply

Interested candidates are invited to submit their resume, detailing their experience with LLMs, LangChain, and Google Cloud AI services.