Senior ML Backend Engineer Search & Recommendations

About the Role: Senior ML Backend Engineer - Search & Recommendations

Salla, a leading e-commerce platform in MENA serving over 68,000 merchants, is seeking a Senior ML Backend Engineer for its AI team. This full-time position is based in Makkah, Makkah Province, and requires 5-10 years of experience. The role focuses on owning the online systems that transform catalog changes into ranked results for shoppers, encompassing search, retrieval, recommendation serving, streaming data, and experimentation.

Role Context and Impact

The AI team at Salla is developing a self-owned discovery stack for its marketplace and merchant stores, featuring hybrid lexical and vector search, Arabic-first query understanding, and learned ranking shared between search and recommendations. While data scientists manage the relevance and ranking models, this role is responsible for the platform that ensures these models are fast, fresh, reliable, and shippable. The work distribution is approximately half online serving, one-third streaming data, and the remainder dedicated to integration into product surfaces. This position is part of the ML Platform team, collaborating daily with search data scientists and the ranking lead.

Key Responsibilities

• Online Serving:

  • Build and operate query and recommendation serving systems, including retrieval, score fusion, filtering, and caching.
  • Adhere to strict latency budgets, targeting double-digit-millisecond p95 for search-as-you-type.
  • Design graceful degradation mechanisms to maintain serving stability when models or vector paths experience slowdowns or outages.
  • Implement experiment infrastructure, including shadow traffic, A/B assignment, guardrail metrics, and rollback capabilities.

• Streaming Data:

  • Develop change-data-capture pipelines from source systems to search indexes and feature stores, with measured freshness.
  • Ensure embeddings remain current for new and updated items.
  • Execute zero-downtime reindexing for multi-million-document collections.
  • Build feature logging systems to convert production traffic into training data for ranking models.

• Integration:

  • Integrate changes into product teams' backends and clients, including new endpoints, cutovers, and experiment flags.
  • Collaborate with product engineering teams on reviews, release windows, and production ownership.

• Operability:

  • Establish and maintain monitoring, alerting, and runbooks for deployed systems.
  • Participate in on-call rotations for owned systems.

Experience Required

• Candidates should possess 5-10 years of relevant professional experience.

Work Environment

This is a full-time position located in Makkah, Makkah Province. The role involves working within the ML Platform team and close collaboration with search data scientists and the ranking lead.