AI Engineer

About UnosecurFounded by Santhosh Jayaprakash and headquartered in Berlin, Unosecur is a fast-growing, Pre-Series A startup with $5M in funding. We are a B2B security SaaS platform making identity security smarter and simpler for enterprises worldwide.You’ll be part of a diverse team working on cybersecurity and AI, with opportunities to solve complex problems and build production-grade AI capabilities.What Your Experience Will BeYou will sit on the Engineering team and own the design and development of Unosecur’s Generative AI and agentic capabilities, including LLM-backed services, agent orchestration, and the architecture connecting AI systems to the security platform.You’ll work closely with the founding and senior engineering team and partner with backend, cloud, and product teams.Your toolkit will span:LLMs and Small Language Models (SLMs)LangChain and LangGraphMCPRAG pipelinesVector and embedding databasesAWS Bedrock and Google Vertex AIAWS / GCP cloud infrastructureThis is a Bengaluru-based role.Why You Belong Here & How You’ll GrowThis is a small, senior team where engineers are expected to take ownership from system design through production deployment.You’ll have the opportunity to:Set technical direction for AI capabilities within the product.Mentor engineers and act as a technical reference point for GenAI.Work closely with founders and senior engineering leadership.Build production-grade AI systems across a wide technical surface area.Grow as an architect, hands-on GenAI engineer, and technical leader.What Success Looks LikeGenAI & Agentic SystemsDesign and architect end-to-end GenAI and agentic systems, from problem framing through orchestration, retrieval, and production deployment.Build agentic workflows using LangChain, LangGraph, and MCP.Integrate tools, plugins, and external data sources with clear permission and failure boundaries.RAG & RetrievalBuild and continuously improve RAG pipelines.Evaluate retrieval quality and improve retrieval performance.Work with vector and embedding databases.Model StrategyOwn model-selection strategy across LLMs and SLMs.Balance model quality, latency, cost, security, and data-handling requirements.Engineering & ReliabilityBuild reliable and scalable AI services capable of running at production load.Improve observability, quality, and reliability across AI systems.Partner with Product and Security teams to translate ambiguous problems into safe, well-architected AI capabilities.Technical LeadershipMentor engineers across GenAI initiatives.Act as the technical reference point for Generative AI within the engineering team.Requirements10+ years of overall engineering experience, including 3+ years of hands-on experience with Generative AI / LLM-based solutions.Demonstrated experience designing and architecting AI solutions, not just implementing or consuming AI tools.Ability to demonstrate AI systems personally designed and built.Strong expertise in the GenAI/agentic stack, including:LangChainLangGraphMCPRAGVector databasesMultiple LLMs / SLMsStrong engineering fundamentals, including:Data structuresProblem-solvingScalable distributed servicesWorking knowledge of GenAI platforms such as AWS Bedrock, Google Vertex AI, or similar.Experience with AWS or GCP and cloud security fundamentals.Strong ownership and builder mindset.Comfortable operating in startup environments with ambiguity.Strong judgment when making architecture and technical trade-offs.Nice to HaveOpen-source AI contributions or substantial hands-on experience with open-source AI projects.Experience building AI into security, identity, or compliance-sensitive products.Experience with RAG evaluation tooling such as Ragas.Structured approaches to measuring and improving AI quality.Product-based or startup experience with end-to-end system ownership.