Description:
At EvenUp, the Machine Learning Team is pivotal in leveling the playing field in legal disputes. We tackle challenging problems at the intersection of ML, information retrieval, and generative AI to create meaningful impact for plaintiffs and attorneys. As a Machine Learning Engineer, you will contribute to building scalable, innovative solutions in the domain of Document AI, working on complex legal data and leveraging cutting-edge techniques to deliver actionable insights and transformative results.
This role provides a unique opportunity to work with a proprietary dataset, solve high-impact problems, and see your contributions lead to real-world justice.
This is a hybrid role with the expectation of working at least 3 days a week from one of our office hubs.
What you'll do:
- Pioneer cutting-edge Document AI systems at the forefront of generative AI innovation, building next-generation models that go beyond traditional document processing to achieve human-level understanding of complex legal and medical documents, intelligently extract key entities and relationships, perform sophisticated multi-document reasoning, and generate contextually-aware documents that transform business workflows.
- Implement and advance technologies in:
- Information Extraction (using traditional ML, LLMs, and multi-modal LLMs for entity recognition, relationship extraction, and document structure understanding)
- Information Retrieval (query understanding, semantic search, hybrid retrieval architectures, and learning-to-rank models)
- Data Management (schema design, knowledge graphs, distributed data pipelines, and petabyte-scale processing)
- RAG (Retrieval-Augmented Generation) with advanced techniques like multi-hop reasoning, chain-of-thought prompting, and self-consistency checks
- Prompt Engineering (few-shot learning, instruction tuning, and context window optimization)
- LLM fine-tuning (parameter-efficient techniques like LoRA/QLoRA, instruction fine-tuning, and domain adaptation)
- Collaborate with domain experts (legal, healthcare, etc), product managers, and engineers to translate insights into robust machine learning systems.
- Create tools that empower internal teams and clients to make data-driven decisions.
- Mentor junior team members, promoting a culture of excellence and collaboration.
What We Are Looking For:
We recognize the breadth of skills required and do not expect candidates to have experience in all areas. We seek talent with a strong foundation in machine learning, information retrieval, or data management, with particular interest in LLM and generative AI technologies.
- 3+ years of experience in machine learning, data science, or similar technical role
- Strong software engineering fundamentals and proficiency in Python
- Demonstrated expertise in:
- Classical ML techniques (regression, classification, clustering)
- Deep learning frameworks (PyTorch, TensorFlow)
- Natural language processing and information extraction
- Large language models and prompt engineering
- RAG system design and implementation
- Advanced RAG techniques (multi-hop reasoning, self-consistency)
- Vector databases and embedding techniques
- Model evaluation and validation methods
- Experience with:
- LLM fine-tuning (LoRA, QLoRA, instruction tuning)
- Knowledge graph construction and reasoning
- Production ML system deployment
- Distributed computing and data processing
- Excellent communication skills with ability to:
- Explain complex technical concepts clearly
- Collaborate effectively with cross-functional teams
- Write clear technical documentation
- Sound judgment in balancing technical tradeoffs with business needs