About
Job Description We’re hiring an experienced AI Engineer with deep LLM experience to build the next generation of legal intelligence tools. You’ll fine-tune models, design RAG pipelines, and build robust evaluation systems all while shaping product direction in a fast-moving startup.
Responsibilities
Fine-tune and deploy LLMs (e.g., LLaMA, Mistral, Claude) for legal document analysis
Design and implement Retrieval-Augmented Generation (RAG) pipelines for clause-based Q&A
Optimize inference workflows for latency, accuracy, and cost-efficiency
Develop tools for prompt engineering, testing, and prompt versioning
Collaborate with product and legal SMEs to shape AI features and interfaces
Evaluate model performance using relevance, accuracy, and hallucination metrics
Required Skills
7+ years in ML/AI engineering roles, with a focus on NLP or LLMs
Strong experience with model fine‑tuning, RAG architectures, and transformer-based models
Proficiency in Python and deep learning frameworks (PyTorch, JAX, Hugging Face)
Familiarity with vector databases (Pinecone, Weaviate, FAISS)
Experience deploying LLMs in production with LLMOps or MLOps stacks
Preferred Skills
Background in legal tech, document automation, or compliance tools
Experience with LangChain, LlamaIndex, and prompt chaining frameworks
Understanding of AI ethics and hallucination mitigation strategies
Fully remote setup with flexible hours
Annual learning stipend + GPU compute access
Comprehensive health benefits and wellness perks
Applicants must be authorized to work in the U.S. We cannot sponsor visas now or in the future.
#J-18808-Ljbffr
Languages
- English
Notice for Users
This job comes from a TieTalent partner platform. Click "Apply Now" to submit your application directly on their site.