About the job
The AI/ML Engineer builds AI capabilities from prototype to production. You will develop prompt engineering solutions, RAG pipelines, AI agents, and evaluation frameworks — starting with rapid prototypes to validate use cases, then engineering them into scalable, production-grade systems. This role requires both the creativity to explore what's possible and the rigor to build what's reliable.
Responsibilities
Prototype AI solutions to rapidly validate use cases and demonstrate feasibility
Scale successful prototypes into production-grade systems with reliability, monitoring, and maintainability
Implement prompt engineering solutions optimized for legal use cases
Build and optimize RAG (Retrieval-Augmented Generation) pipelines using vector databases and knowledge graphs
Develop context engineering approaches that leverage the semantic layer for improved accuracy
Implement grounding mechanisms to reduce hallucinations and improve factual accuracy
Build evaluation frameworks to measure AI accuracy, relevance, and safety across use cases
Integrate AI capabilities with legal workflows (CLM, matter management, eBilling)
Develop AI agent solutions for automation use cases across legal operations
Implement guardrails and safety mechanisms for production AI systems
Collaborate with AI Architect on system design and technical standards
Support AI Product Developers with APIs, integration patterns, and technical guidance
Qualifications
Minimum
4+ years of delivering solutions in AI/ML engineering, NLP, or related roles
Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow, or similar)
Experience with LLM APIs (OpenAI, Anthropic, or similar)
Experience with RAG architectures and vector databases
Understanding of prompt engineering techniques and best practices
Experience taking AI systems from prototype to production
Experience with evaluation frameworks for AI systems
Supporting AI applications in production
Preferred
Experience with LangChain, LlamaIndex, or similar LLM orchestration frameworks
Experience with agentic AI frameworks (LangGraph, CrewAI, or similar)
Familiarity with knowledge graphs and GraphRAG patterns
Experience with AI evaluation tools (RAGAS, DeepEval, or similar)
Knowledge of legal domain and legal NLP applications
Experience with guardrails and safety frameworks (Guardrails AI, NeMo Guardrails)
Understanding of MCP (Model Context Protocol) or similar integration patterns
Experience deploying and monitoring AI systems at scale
Track record of shipping AI products that users rely on