Senior ML Engineer (LLM / RAG)

About Datica
At Datica, we are building an AI-powered LegalTech platform that uses Large Language Models (LLMs), AI Agents, and Retrieval-Augmented Generation (RAG) to transform legal research, document analysis, drafting, and other legal workflows.
Our platform helps individuals, lawyers, and businesses understand legal information, work with legal documents, and complete complex legal tasks more efficiently.
We are looking for a Senior ML Engineer to help design, build, and improve the AI systems at the core of our product. You will work on large language models, retrieval systems, legal datasets, evaluation pipelines, and production AI infrastructure.
Responsibilities

• Design, develop, and improve LLM-powered features across Datica’s products.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for large-scale legal datasets.
• Develop retrieval, ranking, reranking, and document-processing systems.
• Design and improve embedding, chunking, indexing, and search strategies.
• Build evaluation frameworks for measuring retrieval quality, answer accuracy, hallucination, and overall system performance.
• Experiment with prompting, fine-tuning, model selection, and other techniques to improve legal reasoning and response quality.
• Develop pipelines for processing, cleaning, structuring, and enriching large volumes of Persian legal data.
• Work on classification, information extraction, entity recognition, clustering, and other NLP tasks.
• Build reliable and scalable ML services for production environments.
• Monitor model performance, latency, cost, and quality in production.
• Collaborate closely with backend engineers, product teams, and legal experts.
• Contribute to technical architecture and long-term ML strategy.
• Research and evaluate new models, frameworks, and approaches relevant to Datica’s AI stack.

Requirements

• 5+ years of professional experience in Machine Learning, NLP, or a closely related field.
• Ability to independently own complex ML problems from research and experimentation through production deployment.
• Strong Python programming skills.
• Strong understanding of modern NLP and large language models.
• Hands-on experience building LLM-based applications in production.
• Strong experience with Retrieval-Augmented Generation (RAG).
• Experience with vector databases, embeddings, semantic search, and information retrieval.
• Experience designing and evaluating ML or LLM systems.
• Strong understanding of model evaluation metrics and experimentation methodologies.
• Experience working with large and complex datasets.
• Familiarity with model serving, APIs, and production ML systems.
• Experience with Git and collaborative software development.
• Strong problem-solving and analytical skills.
• Experience fine-tuning or adapting open-source LLMs.
• Experience with reranking models and advanced retrieval architectures.
• Experience with Hugging Face, PyTorch, or similar ML frameworks.
• Experience with Elasticsearch, OpenSearch, FAISS, Qdrant, Milvus, or similar retrieval technologies.
• Strong understanding of knowledge graphs or GraphRAG architectures.
• Experience with document parsing, OCR, PDF processing, and unstructured data pipelines.
• Strong understanding of agentic AI systems and multi-agent architectures.
• Experience with LLM observability, tracing, and evaluation tools.
• Familiarity with MLOps, Docker, cloud infrastructure, and CI/CD.
• Experience leading technical projects or mentoring ML engineers.

Tech Stack
Python • LLMs • RAG • PyTorch • Hugging Face • Vector Databases • Elasticsearch • REST APIs • Docker
What We Offer

• Work on challenging AI problems in a highly specialized domain.
• Opportunity to work with large and unique legal datasets.
• Meaningful ownership over the architecture and development of Datica’s core AI systems.
• Opportunity to shape our ML and LLM strategy from an early stage.
• Work closely with legal experts, product teams, and engineers to build production AI systems.
• Collaborative and engineering-driven startup culture.
• Flexible working hours.
• Competitive salary based on experience.
• Opportunity to experiment with state-of-the-art models, retrieval techniques, and AI architectures.

To apply, please send us your CV together with your GitHub profile, research work, publications, or examples of ML/AI systems you have previously built.