You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
SoundCloud

Senior Machine Learning Engineer - Recommendations (Core)

  • Office
  • 6+ years

Salary

Not stated

Similar roles pay £30K - 155K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The team is ML Core, which builds the shared ML models behind the company's recommendations, search and content understanding.

New music starts on the platform. The team connects artists with the listeners most likely to connect with their work, and helps listeners find tracks and emerging scenes they would not reach alone.

Recommendations is the largest area, but the work spans related problems that rely on the same foundations: representing users, tracks and creators, and ranking them.

The stack is being modernized, moving key models from classical methods to deep learning on GPUs.

Responsibilities

  • Design, train and ship models for candidate generation, user and item modeling, and ranking in recommendations, plus related search and content understanding work.
  • Lead the migration of core models from classical methods such as word2vec-style embeddings to PyTorch models trained and served on GPUs.
  • Adapt, fine-tune and assess open-source embedding and ranking models for the catalog and the team's use cases.
  • Own evaluation from start to finish: offline metrics, A/B tests, and confirming that offline gains carry over to live results.
  • Partner with ML, data and backend engineers to deploy models and keep them running well, and help shape modeling standards for the team.

Requirements

  • At least 3+ years building production ML systems, including end-to-end ownership of at least one ranking, retrieval or recommendation model.
  • Strong deep learning skills in PyTorch or a similar framework, with a solid understanding of recommendation and retrieval basics (embeddings, two-tower models, learning to rank, multi-objective ranking) and their trade-offs.
  • Proven experience evaluating and experimenting with ranking systems, including bias in implicit feedback such as clicks and plays.
  • Strong Python skills, comfort with large-scale data processing (for example Spark or BigQuery), and experience deploying models on a cloud platform, with GCP preferred.
  • A master's degree (M.Sc.) in a quantitative field, or equivalent experience.
  • Experience fine-tuning or serving transformer-based embedding or ranking models would be a plus.
  • Experience applying LLMs or foundation models to recommendations, such as content understanding, semantic IDs, generative retrieval or feature generation, would be a plus.
  • Experience with audio, music or multimodal ML would be a plus.
  • Experience with contextual bandits, reinforcement learning or causal methods for long-term value would be a plus.
  • Publications at venues such as RecSys, KDD, SIGIR, WSDM, NeurIPS or similar would be a plus.
  • Experience with ANN or vector search, and with GPU training or serving at scale, would be a plus.
  • You are encouraged to apply even if you do not meet every qualification. Many people doubt their fit, so apply if the role interests you.

Conditions

Equal opportunity applies to all candidates.

Where you’d work

From the office

About the company

SoundCloud

Office in London, United Kingdom

Also hiring in New York, United States

Your chances

We've checked whether it's still hiring and how crowded it is.

  • 19 checks run
  • 0 red flags

Still hiring?

13 checks

No red flags

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details10 facts · Role, Location, Compensation
Tech stack
  • Python
  • PyTorch
  • Spark
  • BigQuery
  • LLMs
  • Vector databases
Seniority
Senior
Specialty
ML
Region
United Kingdom
Pay period
Annual
Show 5 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Seniority
Senior
Experience
3+ years
Tech stack
  • Python
  • PyTorch
  • Spark
  • BigQuery
  • LLMs
  • Vector databases

Location

Work model
Office
Region
United Kingdom
Office
  • London, United Kingdom

Compensation

Salary
Salary by agreement
Pay period
Annual

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason