Principal ML Engineer

Our engineering group is split into roughly 60 product teams, each owning its services end to end, with on-call shared across time zones.

About the role

Larchwood Labs is looking for a Principal ML Engineer to join a small, steady team. We're looking for an engineer to build retrieval-augmented generation features on hosted and open-weight language models, with proper evaluation. This role is fully remote within Germany. Few meetings, lots of written updates. We use Slack, Notion and Google Meet. Cameras on for team calls.

What you'll be doing

• Monitor models for drift, data quality issues and latency regressions
• Set up evaluation harnesses and regression tests for model quality
• Develop RAG pipelines with embeddings, vector stores (pgvector, Pinecone, Weaviate) and rerankers
• Deploy models behind low-latency APIs with FastAPI, Triton, TorchServe or vLLM
• Cut inference cost with quantization, batching and caching
• Fine-tune open-weight models with LoRA when it beats prompting

Required qualifications

• 7+ years of software engineering experience, with at least two spent on ML systems in production
• Comfortable with SQL and large-scale data processing in Spark or Ray
• BS or MS in computer science, engineering or a related field
• Experience deploying models as services and monitoring them

Preferred qualifications

• Published papers or open source ML contributions
• Recommendation or ranking systems at scale

Salary: €143,000 - €174,000 annually

What you get

• Company pension scheme
• Holiday pay
• Home office equipment
• Urban Sports Club membership
• Meal allowance
• Up to 3 days of home office per week

Only shortlisted candidates will be contacted.

Start: Within 30 days.

Demo job created on 11jobs for testing and demonstrations. It is not an actual opening at Larchwood Labs.