Senior Software Engineer – Agentic AI Foundations

Why Socure? Socure is building the identity trust infrastructure for the digital economy — verifying 100% of good identities in real time and stopping fraud before it starts. The mission is big, the problems are complex, and the impact is felt by businesses, governments, and millions of people every day. We hire people who want that level of responsibility. People who move fast, think critically, act like owners, and care deeply about solving customer problems with precision. If you want predictability or narrow scope, this won’t be your place. If you want to help build the future of identity with a team that holds a high bar for itself — keep reading. About the Role As a Senior Software Engineer on the Agentic AI Foundations team, you will be one of the founding engineers responsible for designing and building the core platform, systems, and primitives that enable Socure to transition from traditional software workflows to agent-native operations. You will work across applied AI, platform engineering, and system design to create a secure, evaluable, vendor-agnostic agent platform that other teams across Socure can build on. This is a zero-to-one role with outsized impact: you will shape the architecture, reliability, and safety of agentic systems that power critical internal workflows and, over time, customer-facing products. You will be expected to operate with a high degree of ownership and autonomy, partnering closely with leaders in Platform, Product, Data Science, and other engineering teams to deliver high-impact agent-powered workflows and establish best practices for building secure, observable, and scalable agent systems. What You’ll Do: - Design and build a vendor-agnostic agent platform, including orchestration, tool use, memory, and runtime systems that can be reused across multiple workflows and teams. - Develop evaluation and reliability frameworks (metrics, harnesses, pipelines) to measure and improve agent performance, robustness, and safety in production. - Implement safety and governance controls such as guardrails, policy enforcement, and human-in-the-loop review mechanisms to ensure responsible agent behavior and compliance with internal and external standards. - Build systems for data grounding, retrieval, and memory that enable agents to be accurate, context-aware, and aligned with Socure’s domain knowledge and policies. - Prototype, iterate on, and productionize agent behaviors including planning, multi-step execution, and coordination of tools and services, using real internal workflows as proving grounds. - Partner with product and engineering teams across Socure to identify high-impact use cases, jointly design agent-powered workflows, and launch them into production using the platform primitives you build. - Define and document best practices, design patterns, and paved paths for building secure, observable, and scalable agent systems, and mentor other engineers on how to apply them. - Contribute to the team’s strategy and roadmap by informing architecture choices, identifying technical risks, and helping prioritize foundational investments (e.g., tracing, evaluation approaches, dev tooling). - Uphold and model Socure’s leadership expectations for senior engineers: operating with strong product and systems thinking, influencing without authority, collaborating across functions, and raising the technical bar for the team. What You’ll Bring - 5+ years of professional software engineering experience with a strong background in large-scale distributed systems, backend platforms, or infrastructure. - 3+ years of experience designing, building, and operating production-grade systems with clear reliability, performance, and observability requirements. - Hands-on experience with LLMs, Agentic AI systems, or building intelligent applications (e.g., using modern LLM APIs, orchestration frameworks, or ML-powered services in production). - Demonstrated ability to operate in ambiguity and build from first principles in zero-to-one or highly novel problem areas, including making sound trade-offs under uncertainty. - Strong product and systems thinking: you can connect technical decisions to real-world impact, understand user and business needs, and design systems that balance speed, quality, and safety. - Familiarity with AI safety, security, or policy systems such as guardrails, content filtering, access controls, or audit and compliance mechanisms. - Proficiency in at least one modern backend programming language and ecosystem (e.g., Java, Go, Python, or similar) and comfort working with cloud-native infrastructure, APIs, and data services. - Experience collaborating with cross-functional partners (e.g., product, data science, platform, security) to deliver complex technical initiatives. Preferred Qualifications - Background in multi-agent systems, workflow orchestration, or similar distributed coordination frameworks. - Exposure to building or using agent platforms (e.g., orchestration frameworks, tool registries, memory systems) or advanced prompt/LLM routing, caching, or fine-tuning pipelines. - Experience with evaluation frameworks, experimentation platforms, or ML systems (e.g., offline/online evals, A/B testing, or benchmarking agents and models). - Experience specifically with AI safety, security, or policy systems (guardrails, policy engines, content filters, or responsible AI frameworks). - Experience with retrieval systems, knowledge graphs, or data platforms used to ground LLMs and agents in enterprise context. - Experience in a founding, early-stage, or platform-building role where you defined patterns and paved paths for other teams. Socure is an equal opportunity employer that values diversity in all its forms within our company. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. If you need an accommodation during any stage of the application or hiring process—including interview or onboarding support—please reach out to your Socure recruiting partner directly.