SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Socure is building identity trust infrastructure for the digital economy, verifying identities in real time and stopping fraud before it starts. The Agentic AI Foundations team is transitioning the company from traditional software workflows to agent-native operations.
As a Software Engineer II, you will help design, build, and harden a secure, evaluable, vendor-agnostic agent platform that teams across Socure can build on. This is a hands-on, zero-to-one team where you'll gain outsized exposure to how agentic systems are architected and operated in production, working alongside senior and staff engineers who set architectural direction.
Key responsibilities include:
- Building components of a vendor-agnostic agent platform (orchestration, tool use, memory, runtime systems) under senior engineer guidance
- Implementing evaluation and reliability tooling (metrics, harnesses, pipelines) to measure and improve agent performance, robustness, and safety
- Implementing safety and governance controls (guardrails, policy enforcement, human-in-the-loop review)
- Building data grounding, retrieval, and memory components to keep agents accurate and aligned with domain knowledge
- Prototyping and iterating on agent behaviors using real internal workflows
- Partnering with product and engineering teams to implement agent-powered workflows
- Applying and refining best practices for secure, observable, scalable agent systems
- Contributing strong foundational knowledge of LLMs, GPU computing, and model serving to technical discussions
You bring 2+ years of professional software engineering experience in distributed systems, backend platforms, or infrastructure. You have very strong foundational knowledge of large language models and agentic AI systems, including architectures, prompting patterns, tool use, and evaluation approaches. You understand GPU computing and model-serving infrastructure (CUDA, vLLM, Ollama, TensorRT-LLM, Triton, etc.) and their performance/cost trade-offs. You have solid grounding in distributed systems fundamentals and proficiency in modern backend languages (Java, Go, Python). You work productively in ambiguous, early-stage problem spaces and communicate effectively across technical and cross-functional teams.
