Security & Identity Engineer

This is a fully remote position, open to applicants in Poland.

📋 Description

• Collaborate with an external software development organization as a member of Inviso’s delivery team

• Create and manage AI functionalities within an enterprise platform

• Develop agent runtimes, model routing, RAG, tool/function invocation, guardrails, evaluation, monitoring, cost management, latency optimization, and quality control for production

• Transition AI functionalities from prototype stages to monitored production environments

• Rigorously assess AI behavior

• Work alongside product and engineering teams to identify appropriate AI applications

• Provide AI functionalities that are valuable, dependable, quantifiable, safe, and mindful of costs

• Transform experimental findings into production-ready features

• Incorporate evaluation practices into the delivery process

• Assist client teams in making data-driven decisions regarding the genuine value of AI

• Offer consulting support to clients, including travel as necessary to meet client requirements

⛳️ Requirements

• Proven experience delivering software powered by LLMs, ML models, RAG systems, or agentic workflows to actual production users

• Background in designing or implementing agent runtimes, orchestration, model routing, tool/function invocation, or AI workflow patterns

• Deep understanding of RAG, grounding, retrieval quality, prompt design, context management, and evaluation methodologies

• Experience in building evaluation harnesses, golden sets, regression checks, quality gates, or measurable AI performance frameworks

• Capability to consider cost, latency, reliability, and safety as primary engineering constraints

• Familiarity with creating guardrails and controls for AI systems, addressing untrusted retrieved content, tool output risks, and failure modes

• Experience in monitoring AI behavior in production and enhancing systems based on empirical evidence

• Strong software engineering expertise

• Ability to collaborate effectively with backend, platform, product, and security teams

• Excellent communication and teamwork skills for client-facing consulting scenarios

• Pragmatic approach focused on delivering business value responsibly

• Experience with Claude, GPT, Azure OpenAI, open-source models, model routing, fine-tuning, distillation, or small/edge models

• Familiarity with MCP, A2A, multi-agent orchestration, AI tool invocation, or agent evaluation

• Knowledge of LLM-as-judge methodologies calibrated against human evaluation

• Experience in semantic knowledge management, ontologies, knowledge graphs, or semantic layers

• Familiarity with AI development lifecycle practices, including data handling, building, evaluation, deployment, monitoring, and continuous improvement

• Experience utilizing AI-assisted development tools while upholding review, testing, and safety protocols

🏝️ Benefits

• Paid annual leave and public holidays

• Disability insurance

• Retirement and pension plans

• Unemployment insurance

• Worker compensation insurance

• Maternity leave

• Paternity leave

• Parental leave

• Bereavement leave

• Marriage leave

• Rewarding referral bonus program

• Annual education reimbursement program

• Competitive, equitable, and flexible compensation package