AI Engineer

• Socure is building the future of trust for digital ecosystems
• To accelerate our mission, we are expanding the platform to include agentic workflows and internal productivity tools that power innovation across the company
• These systems will underpin how Socure builds, deploys, and scales AI-driven identity solutions while enabling internal teams to operate with speed, intelligence, and precision
• Reporting to the Head of New Product Engineering, you’ll join a new Internal AI Engineering team with a mandate to design and ship the agentic systems that reshape how Socure operates across sales, marketing, revenue ops, finance, talent, and legal
• As a Staff AI Engineer on this team, you’ll define what to build - not just execute what’s been scoped
• You’ll be the first major internal partner building on Socure’s Agentic AI Foundations platform - using its primitives to ship faster and providing the real-world pull-through that shapes its roadmap
• By delivering intelligent automation and agentic workflows you will play a central role in Socure’s transformation into an AI-native company, driving step-function gains in efficiency, accuracy, and decision-making across the enterprise
• Prioritization of High-Impact Automation - Partner with business teams (e.g., Revenue Ops, Marketing, Finance Ops, Talent Acquisition) to catalog manual, high-frequency workflows and rank them by impact, feasibility, and urgency
• Production Agent Design & Development - Build multi-step, tool-augmented agent workflows that can plan, execute, observe outcomes, and iteratively improve. Design and implement planner–executor and reflection-based architectures to enhance reasoning quality and task reliability. Develop stateful agent systems and incorporate human-in-the-loop controls, including approval gates, fallback paths, and escalation mechanisms
• Platform Integration - Leverage the Agentic AI Foundations team’s platform covering agent runtime, orchestration, memory, tool registry, guardrails, and observability. Provide feedback that shapes platform priorities
• Innovation & Standards - Leverage LLMs, multi-agent frameworks, and orchestration platforms to create differentiated internal solutions that can’t be bought off the shelf. Stay ahead of emerging AI technologies and regulatory frameworks to ensure Socure leads the industry in secure, compliant, and intelligent internal systems
• Technical Patterns - Discover reusable agent design patterns while building real workflows and contribute them back to the Agentic AI Foundations paved paths so the work compounds across Socure
• Operational Excellence - Leverage the evaluation harness and tracing substrate provided by Agentic AI Foundations for continuous performance assessment, failure-mode analysis, and optimization of speed and accuracy of specific agentic solutions

Benefits

• Health: Comprehensive medical coverage, including vision, dental, and FSA
• Parental Leave: Generous leave allowance for
  parents-to-be
• 401k: Pre-tax savings for retirement
• Life Insurance: Protect your family in
  case of emergency
• PTO: Take as much time as you need,
  when you need it
• 100% Remote: Work from anywhere anytime, whatever suits your lifestyle
• WFH Allowance: Generous reimbursement program to maximize your WFH setup
• Deskpass: Work in an office environment whenever you feel the need
• Mental Health Provider: Connect with clinicians when you need it
• Learning & Development: Self-education allowance & free career coaching
• Employee Assistance Program “EAP”: Lifestyle resources available as well as additional mental health resources
• Fertility Provider: Family planning solutions for those interested
• Personal Legal Support: Significant discounts with RocketLawyer- Deep hands-on experience with LLM APIs and at least one agentic framework (e.g. LangGraph, CrewAI or AutoGen)
• Strong systems thinking: you design for reliability, observability, and maintainability from day one, not as an afterthought
• Experience shipping AI/automation solutions that directly impacted business operations
• Proven ability to operate in ambiguity: you’ve walked into an undefined problem space, figured out what to build, built it, and measured the results
• 8+ years of software engineering experience, with at least 2 years focused on AI/ML systems or LLM-powered applications in production
• Strong Python skills and experience building production-grade backend services, APIs, and data pipelines
• Ability to collaborate directly with non-technical business stakeholders to understand their actual workflows and translate those into technical solutions
• Experience with multi-agent systems, workflow orchestration, or complex tool-use patterns in production
• Familiarity with evaluation frameworks (e.g., LangSmith, Weights & Biases, Arize, or custom eval pipelines) for AI systems (agent reliability, accuracy benchmarking, failure-mode analysis)
• Experience with RAG pipelines, vector databases, knowledge graphs, or memory/grounding systems
• Experience with real-time or streaming AI systems
• Familiarity with AI safety and security practices, including prompt injection prevention, hallucinations mitigation and data protection/privacy
• Background in a regulated industry (fintech, healthcare, government) where compliance and security review processes are standard
• Experience with agent skill abstraction and structured tool integration via MCP (Model Context Protocol), function calling or similar protocols
• Experience with AWS-hosted LLM infrastructure (Bedrock, AgentCore/Strands, Lambda, SageMaker) or equivalent cloud ML services