ML Engineer (Platform & Multimodal Retrieval)

emagine Polska

Stockholm, Sweden • 46m ago • On-site

Senior

On-site

  1. Select offer
  2. Add resume
  3. Analyze
  4. Improve
  5. Apply
  6. Auto-send · soon

Match your resume with similar open roles

Upload your resume to automatically match with active openings similar to this role.

PDF up to 10 MB

Your resume is private & secure

Quick Facts

  • Role: ML Engineer (Platform & Multimodal Retrieval)

  • Contract: 9–12 months (full-time)

  • Location: Stockholm (at least 2 days/week in-office)

Description

You will support an AI foundations team by improving the developer experience of an ML training/orchestration platform and by building a shared multimodal retrieval layer for podcasts and video. Work across two tracks: make Flyte orchestration, experiment tracking, and model serving more reliable and easier to use; and productionalize transcript-based podcast embeddings and extend the approach to video, including embedding evaluation and retrieval quality.

Responsibilities

  • Improve a Flyte-based orchestration platform (faster iteration, observability/debugging, reusable templates/documentation)

  • Standardize experiment tracking and model shipping via MLflow conventions and golden paths from experiment to production

  • Develop and optimize Triton-based model serving (latency/cost via caching, scaling, GPU strategies, backends)

  • Listen to platform users and prioritize improvements based on where teams lose time

  • Build a multimodal retrieval foundation:

    • Create a reliable, observable, cost-efficient podcast embedding pipeline (Flyte orchestration, transcript segmentation, schema/indexing in Vespa, retrieval evaluation)
    • Extend to video using transcript-based chunking and reuse the podcast pipeline
    • Evaluate native video/multimodal embeddings against the transcript baseline and recommend what to adopt
  • Provide documentation and handover (runbooks, architecture notes, knowledge-sharing)

  • Share learnings to raise AI literacy across data scientists and engineers

Requirements

  • 4+ years of experience as an ML engineer / ML platform engineer (or similar)

  • Experience moving ML systems from experiment to production

  • Strong Python skills with tested, clean code

  • Hands-on experience with ML orchestration and experiment tracking (Flyte and MLflow preferred)

  • Experience with model serving/inference optimization and working knowledge of GPU workloads

  • Working knowledge of Docker and Kubernetes; comfortable troubleshooting with logs/metrics/traces

  • Practical experience with embeddings and retrieval (embedding at scale, vector/hybrid search, retrieval quality evaluation)

  • Familiarity with Git, CI/CD (GitHub Actions), and modern cloud-native environments

  • Product mindset for internal platforms (developer experience, documentation, migration paths)

  • Clear communication to explain solutions to non-technical colleagues

Benefits

  • Time-limited engagement with clear handover expectations (runbooks, architecture notes, and knowledge-sharing)

  • Opportunity to strengthen both the ML platform developer experience and a shared multimodal retrieval foundation for media search/recommendations

See similar jobs

Explore similar jobs and use your resume score to choose where to apply next

See more

Unlock Full Resume Report