Socure
AI Engineer
Hub - San Francisco, Remote. Posted 5 months ago
The role
You will design and ship agentic systems and intelligent automation to reshape how Socure operates across various business departments. You will build multi-step, tool-augmented agent workflows and leverage the Agentic AI Foundations platform.
What you will do
- Partner with business teams to catalog and rank manual workflows by impact and feasibility.
- Build multi-step, tool-augmented agent workflows.
- Design and implement planner–executor and reflection-based architectures.
- Develop stateful agent systems with human-in-the-loop controls.
- Leverage the Agentic AI Foundations platform for agent runtime, orchestration, and memory.
- Provide feedback to shape platform priorities.
- Use LLMs and multi-agent frameworks to create internal solutions.
- Discover and contribute reusable agent design patterns.
- Use evaluation harnesses and tracing substrates for performance assessment and optimization.
Required qualifications
- 8+ years of software engineering experience
- At least 2 years focused on AI/ML systems or LLM-powered applications in production
- Deep hands-on experience with LLM APIs
- Experience with at least one agentic framework (e.g. LangGraph, CrewAI or AutoGen)
- Strong Python skills
- Experience building production-grade backend services, APIs, and data pipelines
- Proven ability to operate in ambiguity
- Experience shipping AI/automation solutions that directly impacted business operations
- Strong systems thinking for reliability, observability, and maintainability
- Ability to collaborate directly with non-technical business stakeholders
Nice to have
- 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)
- 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
- Background in a regulated industry (fintech, healthcare, government)
- Experience with agent skill abstraction and structured tool integration via MCP, function calling or similar protocols
- Experience with AWS-hosted LLM infrastructure (Bedrock, AgentCore/Strands, Lambda, SageMaker) or equivalent cloud ML services
About the company
Socure is building the identity trust infrastructure for the digital economy by verifying identities in real time and stopping fraud. The company aims to build the future of identity with a team that holds a high bar for itself.