Senior Machine Learning Engineer - Systems

EvenUp is on a mission to close the justice gap using technology and AI, empowering personal injury lawyers and victims to achieve better outcomes. The Senior Machine Learning Engineer will develop and deploy models for the company's proprietary claims-intelligence platform, focusing on machine learning, natural-language processing, and generative AI.

Responsibilities:

• Design and implement end-to-end ML systems for retrieval-augmented generation (RAG), vector search, and fine-tuning pipelines
• Build and optimize data pipelines that integrate structured, unstructured, and embeddings-based data into ML workflows
• Develop frameworks and reusable components for data extraction, evaluation, and benchmarking of LLMs and other models
• Collaborate with data scientists and product teams to translate business problems into ML system designs
• Research, prototype, and productionize state-of-the-art techniques in semantic search, embeddings, and prompt engineering
• Implement evaluation strategies for ML systems, including relevance metrics, quality scores, and human-in-the-loop workflows
• Ensure scalability and efficiency of ML workflows, including large-scale embedding generation and retrieval pipelines
• Work with machine learning platform engineers to integrate ML frameworks into production environments
• Document system architectures and create internal best practices for building ML/AI frameworks

Requirements:

• Design and implement end-to-end ML systems for retrieval-augmented generation (RAG), vector search, and fine-tuning pipelines
• Build and optimize data pipelines that integrate structured, unstructured, and embeddings-based data into ML workflows
• Develop frameworks and reusable components for data extraction, evaluation, and benchmarking of LLMs and other models
• Collaborate with data scientists and product teams to translate business problems into ML system designs
• Research, prototype, and productionize state-of-the-art techniques in semantic search, embeddings, and prompt engineering
• Implement evaluation strategies for ML systems, including relevance metrics, quality scores, and human-in-the-loop workflows
• Ensure scalability and efficiency of ML workflows, including large-scale embedding generation and retrieval pipelines
• Work with machine learning platform engineers to integrate ML frameworks into production environments
• Document system architectures and create internal best practices for building ML/AI frameworks
• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus, Elasticsearch/OpenSearch)
• Familiarity with retrieval frameworks (LangChain, LlamaIndex, custom retrieval pipelines)
• Strong software engineering skills (Python, distributed computing, APIs)
• Strong knowledge of transformer models (LLMs, embeddings, fine-tuning methods like LoRA, PEFT)
• Understanding of evaluation methodologies for generative AI (RAG benchmarks, hallucination reduction, factual grounding)