SlashMobility is a boutique technology firm specialising in supporting organisations at critical stages of their digital transformation, combining technology talent (Tecno Élite), business insight and a high-performance culture.Our focus goes beyond delivering projects: we provide Tecno Élite talent capable of accelerating digital transformation and creating value with a measurable impact on technology and business.What You’ll DoCore Responsibilities:Design Agentic AI Workflows: Build multi-step AI workflows using LangGraph or similar frameworks to solve claims leakage detection problemsPrompt Engineering: Develop and optimize prompts for LLMs to extract insights, reason about claims data, and identify leakage patternsStructured Data Modeling: Create Pydantic models that enforce schema validation and provide control over LLM reasoning outputsExperimentation & Evaluation: Design experiments, define hypotheses, implement evaluation frameworks, and provide evidence-based conclusionsHypothesis Validation: Collaborate with the team to validate findings before integration, ensuring all solutions are backed by rigorous evaluationIterative Development: Work in experimental cycles with rapid prototyping, testing, and refinement based on evaluation metricsProduction Implementation: Translate validated experiments into production-ready components with proper error handling, logging, and monitoringCross-Team Collaboration: Work alongside other AI Engineers to align on evaluation methodologies, share findings, and integrate solutionsMust Have3-5 years of experience in software engineering, data science, or AI engineeringStrong Python skills with focus on data processing, ML pipelines, and production code qualityHands-on LLM experience: Practical experience with LLM APIs (OpenAI, Anthropic, Azure, OpenAI), advanced prompting techniques, and structured outputsAgentic AI workflows: Familiarity with workflow orchestration frameworks (LangGraph, LangChain, CrewAI, or similar) and multi-step agent patternsPydantic or similar: Experience designing typed data models for validation and structured data handlingExperimentation mindset: Track record of hypothesis-driven development, A/B testing, or experimental validation in AI/ML projectsEvaluation expertise: Experience designing evaluation frameworks, curating test datasets, and defining quality metrics for AI systemsEvidence-based approach: Ability to document experiments, present findings with supporting data, and justify technical decisions with evidenceNice to HaveExperience with claims processing, insurance domain, or leakage detection use casesFamiliarity with RAG (Retrieval-Augmented Generation) architectures and vector databasesExperience with LLM observability tools (LangSmith, Langfuse, Weights & Biases, MLFlow)Experience with Databricks for data processing and ML workflowsBackground in statistical analysis, experimental design, or causal inferenceKnowledge of cost optimization strategies for LLM-based systemsExperience with async Python and concurrent processing patternsFamiliarity with CI/CD pipelines, automated testing, and version control best practicesWhat You’ll BringAnalytical rigor: Ability to formulate hypotheses, design experiments, and interpret results with statistical confidenceIterative problem-solving: Comfort with ambiguity and iterative refinement based on experimental feedbackStrong communication: Ability to present findings, document experiments, and explain technical decisions clearlyCollaborative spirit: Experience working in cross-functional teams with shared evaluation standardsQuality focus: Commitment to building reliable, well-tested, and maintainable AI systemsSelf-direction: Ability to work independently while actively seeking feedback and collaboration

Sourced from LinkedIn. Relocantly aggregates public job postings; apply on the original site.

Senior LLM/ML ( Inglés alto-C1)