Note: The job is a remote job and is open to candidates in USA. Entegrata is a startup transforming how the legal industry works with data through Azure-based data lakehouses and AI-powered analytics. The Applied AI + NLP Engineer will build conversational analytics, document intelligence, retrieval, and natural-language-to-query capabilities while ensuring accuracy, governance, and reliability across the platform.
Responsibilities
- Build systems that translate natural language questions into deterministic analytical workflows and governed queries over structured legal data
- Help define and implement semantic models and metadata that enable LLMs and AI agents to reason consistently over operational, business, and legal data
- Improve intent recognition, query planning, and ambiguity resolution to deliver accurate, consistent responses—even when user requests are incomplete or underspecified
- Develop AI agents capable of accessing, interpreting, and synthesizing structured data and legal content to answer complex business questions
- Build orchestration logic that intelligently selects the appropriate data sources, models, tools, and workflows for each request
- Implement guardrails that ensure AI responses align with governed business definitions, semantic models, and firm conventions
- Build evaluation frameworks, benchmark datasets, and automated tests that continuously improve answer quality, determinism, and reliability
- Collaborate with Data Engineering to expose governed metrics, dimensions, relationships, and business logic for AI consumption
- Design and build AI pipelines that transform complex legal documents into structured, machine-understandable data
- Help design and evolve legal data models that capture the key concepts, relationships, and business meaning contained within legal documents
- Develop techniques to identify legal concepts, obligations, timelines, financial terms, parties, and other domain-specific information that populate and enrich those data models
- Design confidence scoring, validation, and human review workflows that improve extraction quality and support continuous model refinement
- Optimize AI workflows for quality, latency, scalability, and cost across the platform
- Partner closely with Product, Data Engineering, and legal domain experts to translate customer needs into production AI capabilities
- Stay current with advances in applied AI, LLMs, and agentic systems, bringing practical innovations into production where they create measurable customer value
- Ramp on the platform, semantic layer, and current AI capabilities and evaluation approach
- Help create or improve a natural-language query or retrieval flow
- Own an end-to-end AI capability, including its evaluation harness and quality metrics
- Deliver the initial design framework for deconstructed legal documents
- Measurably improve answer accuracy or reliability on a defined test set
- Deliver production AI features with strong, measured quality and guardrails
- Set a technical direction for a piece of the AI roadmap and drive it forward
- Establish yourself as a trusted technical partner who can independently design, buils and improve AI capabilities across the Entegrata platform
Skills
- 5+ years of software engineering, with hands-on experience building applied AI, NLP, or ML features in production
- Practical experience with LLMs: prompting, retrieval-augmented generation, agents, and tool use
- Experience with information extraction, document parsing, classification or named entity recognition
- Strong evaluation mindset: building test sets and measuring model and system quality
- Solid SQL and understanding of structured data and semantic layers
- Proficiency in Python and one of Go, .NET, or Node.js
- Focus on accuracy, safety, and reliability in customer-facing AI
- Experience with natural-language-to-SQL or query generation over governed data
- Familiarity with data lakehouse or BI platforms (Databricks, Snowflake, or Microsoft Fabric)
- Experience with vector / semantic search, embeddings, reranking and hybrid retrieval
- Experience building pipelines and processing approaches for long-form or highly structured documents
- Legal, finance, or professional services domain exposure
Benefits
- Medical, dental, and vision insurance
- 401(k) with employer match
- Unlimited PTO and company holidays
- Professional development support
- Flexible remote work
Company Overview