Lead Machine Learning - Search

GO-JEK SINGAPORE PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

GO-JEK SINGAPORE PTE. LTD. is seeking a senior AI/ML engineer to design and optimise hybrid lexical–semantic retrieval pipelines, enhancing GoFood and GoPay surfaces.

You will build high-quality embeddings and relevance signals that capture user intent, cuisine and dish semantics, geolocation, delivery constraints, and promotions. You will develop multi-task deep ranking models balancing conversion, merchant quality, and user retention, leveraging real-time signals such as promotions and stock

Qualifications

• Master’s degree or higher in CS/ML/NLP/CV related fields.
• Hands-on experience building large-scale ranking or recommendation systems.
• Familiarity with LLMs and LLVMs in search or recommendation contexts.
• Strong ability to translate user behavior into ranking signals.

Responsibilities

• Design and optimise hybrid retrieval pipelines to improve precision and recall.
• Build embeddings and relevance signals for user intent, cuisine, and dish semantics.
• Develop multi-task deep ranking models balancing conversion and retention.
• Create personalised ranking layers using historical orders and contexts.
• Engineer recommendation algorithms including graph-based methods and sequence models.
• Advance embedding quality for multi-modal data and use LLMs to enhance knowledge.
• Incorporate taxonomy signals and knowledge-graph features into retrieval pipelines.

Skills

Python

C++

Java

NLP

ML

Ranking systems

Recommender systems

LLMs

LLVMs

Communication

Education

Master’s degree or higher in Computer Science or related field

Tools

BM25

HNSW

LSH

Dense vectors

Graph-based methods

Python tooling

Job description

What will you do?

• Design and optimise hybrid lexical–semantic retrieval pipelines (e.g., BM25, dense vectors, HNSW/LSH, generative retrieval) to improve precision and recall across GoFood and GoPay surfaces.
• Build high-quality embeddings and relevance signals that capture user intent, cuisine and dish semantics, geolocation, delivery constraints, price sensitivity, and promotions.
• Develop multi-task deep ranking models that balance conversion, diversity, merchant quality, and long-term user retention, integrating real-time signals such as promotions, surge, and stock availability.
• Build personalised ranking layers and user behaviour models leveraging historical orders, preferences, and contextual features.
• Engineer recommendation algorithms using collaborative filtering, graph-based methods, and sequence models for retrieval expansion (e.g., Q2Q2I, Q2I2I, U2I), including for cold-start merchants and new dishes.
• Advance embedding quality for multi-modal data (text, images, behavioural signals) and use LLMs to enhance structured knowledge (taxonomy tagging, dish attributes, dietary labels).
• Incorporate structured metadata, taxonomy signals, and knowledge-graph features into retrieval and ranking pipelines to improve semantic understanding and consistency.

What you will need?

• Master’s degree or higher in Computer Science, Machine Learning, NLP, CV, or a related field; strong programming skills in Python, C++, or Java.
• Hands‑on experience building large‑scale ranking or recommendation systems in consumer products (ecommerce, food delivery, rideshare, ads, streaming, social).
• Familiarity with LLMs and/or LLVMs. Experience integrating them into search or recommendation pipelines is a strong plus.
• Demonstrated ability to innovate with new algorithms or tools and drive measurable impact, especially making use of Large language Models (LLMs) and Large Language and Vision models (LLVMs) in search or recommendation modeling.
• Strong product intuition and ability to reason from user behavior data and traffic patterns.
• Good communication skills in English, both written and verbal.
• Self‑motivated, curious, and excited by the opportunity to build high‑impact systems quickly.