Python Developer; AI​/ML

We are hiring a Python Developer with strong AI/ML expertise to design and scale our intelligent document processing and legal reasoning systems. You will work on RAG pipelines, graph databases, and LLM optimization to power Space Lizit's core AI capabilities that automate complex immigration workflows for US law firms.

Space Lizit is building the AI layer for US immigration law — automating petitions, predicting RFE risk, and enabling attorneys to process 10x more cases with AI-driven workflows.

• Design and implement Retrieval-Augmented Generation (RAG) pipelines for legal document processing
• Optimise LLM inference using vLLM, TensorRT, or similar frameworks
• Build and maintain vector search systems (Pinecone, Weaviate, or pgvector)
• Develop prompt engineering strategies for immigration-specific language models

• Model complex immigration case relationships in Neo4j knowledge graphs
• Write optimised Cypher queries for multi-hop relationship traversal
• Build knowledge extraction pipelines from USCIS forms and legal documents
• Design graph-based reasoning systems for case eligibility assessment

• Build production-grade Python APIs using FastAPI or Django REST Framework
• Integrate AI services with the core MERN stack via gRPC or REST
• Implement async task queues using Celery and Redis
• Containerise services with Docker and deploy on Kubernetes / AWS ECS

• Build ETL pipelines for processing USCIS forms, PDFs, and legal documents
• Implement OCR and document intelligence using Amazon Textract or Azure Form Recognizer
• Monitor model performance metrics and implement continuous retraining workflows
• Maintain data quality, lineage, and governance standards

• 3–5 years of professional Python development experience
• Hands-on experience building production RAG or LLM-based systems
• Strong proficiency with Lang Chain, Llama Index, or similar AI orchestration frameworks
• Experience with Neo4j or other graph databases
• Solid understanding of vector embeddings and semantic search
• Proficiency with FastAPI or Django REST Framework
• Experience with Docker, Kubernetes, and cloud platforms (AWS/GCP/Azure)
• Strong algorithmic and data structures fundamentals

• Experience with vLLM, TensorRT, or ONNX for model optimisation
• Knowledge of Apache Kafka or similar event streaming platforms
• Background in NLP, information extraction, or document intelligence
• Familiarity with USCIS forms, immigration processes, or legal-tech
• Open-source AI project contributions

• Strong analytical and systems-thinking mindset
• Ability to translate complex AI concepts for non-technical stakeholders
• Self-directed with the ability to navigate ambiguity in research-driven work
• Collaborative approach to cross-functional engineering
• Clear written and verbal communication in English

• Fully remote — global team across US, India, Singapore, and UAE
• Competitive salary benchmarked against global AI engineering rates
• Direct access to frontier AI research and tooling
• Annual learning & conference budget
• Fast-track impact: your AI directly affects thousands of immigration cases
• Flexible working hours with async-first culture
• Performance bonuses tied to product impact metrics

1. Describe an RAG system you've built — what retrieval strategy, embedding model, and LLM did you use?

2. Have you worked with graph databases? Describe a graph data model you designed and why.

3. What is your experience with LLM fine-tuning vs prompt engineering — when do you choose each?

Send your resume and a brief cover letter explaining why you're a great fit. We review every application personally within 48 hours.