AIML Engineer (LLMs & RAG)

Particula is the prime rating provider for digital assets now bringing trusted data-driven ratings on-chain. As DeFi matures and converges with TradFi were building the rails that help institutions protocols and builders use ratings to unlock safer more efficient capital flows.

About the role

Youll help design build and ship LLMpowered features that underpin our ratings and monitoring products. Working closely with the Head of AI youll focus on AIpowered token and asset analysis automated report generation multimodal document analysis robust evaluation and observability and reliable production delivery on AWS.

No one ticks every box. If you bring solid fundamentals curiosity and the drive to learn quickly please apply even if your experience doesnt align onetoone with the description. We care about potential and attitude.

Tasks

• Build and maintain LLMpowered features endtoend (prompting RAG pipelines structured extraction/classification such as entity extraction).
• Develop data ingestion cleaning and indexing pipelines for RAG including n8n workflows for intake and enrichment (connectors transformations error handling scheduling).
• Contribute to lightweight model tuning and systematic evaluation.
• Establish evaluation and observability for RAG (dashboards automated reporting experiment tracking) to ensure reliability and factual grounding.
• Optimise prompts retrieval and context strategies to improve accuracy reduce hallucinations and control latency/cost.
• Work handinhand with our ML/DevOps engineer to ensure smooth deployments reliability and continuous improvement.
• Coordinate and provide technical guidance to a small offshore AI development team (clear specifications code reviews quality standards) with support from the Head of AI.
• Collaborate with product and engineering to scope and deliver incremental value in short iterative releases.

Requirements

• Strong Python skills; experience with PyTorch or Transformers; familiarity with the Hugging Face ecosystem.
• Practical knowledge of LLM tooling (e.g. LangChain or LangGraph) and RAG concepts.
• Experience building on AWS ideally including:
  Serverless functions (AWS Lambda) for orchestration
  Elastic compute (EC2) for workloads
  Foundation model services (Bedrock or SageMaker) for model hosting and tuning.
• Handson with n8n; workflow automation experience is a plus.
• Containerisation with Docker; proficiency with Git and CI/CD.
• MLOps fundamentals: MLFlow for experiment/model tracking; evaluation frameworks (e.g. RAGAS).
• Clear communication collaborative mindset and focus on shipping.
• Languages: strong English; German is a plus. Applications in English or German are welcome.
• Education: Degree in Computer Science or equivalent preferred; equivalent practical experience acceptable.

Benefits

• Offsites with the team in exciting locations
• Flexible working hours in a remotefirst company
• Exciting product in a very dynamic market environment
• Valuesbased startup culture
• Many opportunities to develop further and network with committed people
• Flat hierarchy

Lets build the next layer of trust for digital assets - together!