Remote opportunity at
SallaSenior ML Backend Engineer - Search & Recommendations
Salla, the prominent e-commerce platform in the MENA region supporting over 68,000 merchants, is looking for a Senior ML Backend Engineer to join its ML Platform…
Career Tools
About This Role
Salla, the prominent e-commerce platform in the MENA region supporting over 68,000 merchants, is looking for a Senior ML Backend Engineer to join its ML Platform team. In this fully remote position, you will own the production systems responsible for transforming merchant catalogue updates into ranked shopping results, including search retrieval, recommendation serving, fresh streaming data, and experiment delivery. This role is well-suited for an experienced engineer who enjoys building…
Job Description
Salla, the prominent e-commerce platform in the MENA region supporting over 68,000 merchants, is looking for a Senior ML Backend Engineer to join its ML Platform team. In this fully remote position, you will own the production systems responsible for transforming merchant catalogue updates into ranked shopping results, including search retrieval, recommendation serving, fresh streaming data, and experiment delivery.
This role is well-suited for an experienced engineer who enjoys building high-throughput infrastructure and collaborating closely with search data scientists and ranking leads. Your time will be divided between online serving, streaming data management, and product surface integration. The team focuses on creating a self-owned discovery stack that features Arabic-first query understanding, hybrid lexical and vector search, and shared learned ranking for both search and recommendations.
You will be responsible for maintaining strict latency performance, designing resilient fallback mechanisms, and managing experimentation infrastructure like A/B assignment and shadow traffic. Additionally, you will handle change-data-capture pipelines, feature logging for future training data, and zero-downtime reindexing processes. Daily tasks also involve collaborating with product engineering teams to deploy changes safely and participating in on-call rotations for the services you operate.
Responsibilities
- Develop and manage query and recommendation serving systems focusing on retrieval, score fusion, filtering, and caching while maintaining strict double-digit-millisecond p95 latency targets for search-as-you-type functionality.
- Implement fallback behaviors to ensure services remain operational when specific models or vector paths slow down or fail.
- Establish experimentation frameworks including shadow traffic, A/B test assignment, rollback procedures, and guardrail metrics.
- Construct change-data-capture pipelines using Kafka or Debezium to feed source systems into search indexes and feature stores with high data freshness.
- Execute zero-downtime reindexing operations for large document collections containing millions of entries.
- Create feature logging mechanisms that convert live production traffic into training datasets for ranking models.
- Collaborate with product engineering teams to release new endpoints, handle cutovers, manage feature flags, and conduct technical reviews.
- Maintain system reliability through monitoring, alerting, runbooks, and share on-call responsibilities for production services.
Requirements
- Minimum of 5 years of professional experience building backend or platform systems in production environments.
- At least 2 years of experience operating a production search engine such as Elasticsearch, OpenSearch, Solr, Typesense, or Vespa.
- Demonstrated ability to design low-latency services under real traffic loads and diagnose p95 latency bottlenecks.
- Practical background in streaming data ingestion using tools like Kafka or Debezium along with idempotent backfill capabilities.
- Proficiency in Python programming and comfort shipping code written in TypeScript.
- Prior experience delivering production changes through staged rollouts and A/B testing frameworks.
- Daily utilization of agentic coding assistants like Claude Code.
Core Skills
Frequently Asked Questions
Answers are based only on the employer’s listing; where it doesn’t say, neither do we.
Is this position remote?
Yes, the posting explicitly lists the location as remote and the remote status as remote.
What is the employment type?
The role is a full-time position.
What salary does this position offer?
The job posting does not specify the salary for this role.
What are the primary technical experience requirements?
Candidates must have at least 5 years of backend or platform system building experience, 2 years operating a production search engine, expertise in streaming ingestion like Kafka or Debezium, strong Python skills, and experience with TypeScript and A/B tests.
Sample Interview Questions
AI-generated questions tailored to this specific role — a preview of the full practice set.
