Senior Data Scientist II – Generative AI & Retrieval

About the role

We are looking for a Senior Data Scientist II to advance AI‑powered legal technology using generative AI, retrieval‑augmented generation and agentic systems. You will design, build and operate production‑grade Python applications that turn complex AI capabilities into reliable customer solutions.

Key responsibilities

• Architect modular agentic applications with clear separation of retrieval, prompting, model invocation, tool execution and state management.
• Refactor legacy Python code to improve readability, modularity, testability and runtime performance.
• Own production readiness for AI components, including input validation, exception handling, retries, fallback behavior and secure credential handling.
• Establish observability through structured logging, metrics, tracing and alerting for LLM and retrieval workflows.

Required profile

• Advanced Python proficiency with strong command of data structures, algorithms, type annotations and complexity analysis.
• Experience turning prototype code into modular, maintainable, observable production systems.
• Proven ability to design resilient distributed applications handling timeouts, retries, partial failures and graceful degradation.
• Solid understanding of production LLM concerns such as output validation, token cost control and security.

Required skills

• Python
• OpenSearch or Solr
• pytest, ruff, mypy and profiling tools
• CI quality gates and automated testing frameworks
• Pydantic for schema validation

What we offer

• Flexible working hours to support work‑life balance.
• Wellbeing initiatives, shared parental leave, study assistance and sabbatical options.