AI Engineer
Agentic Ai
Ai Agent
Ai Agent Platform
Ai Platform
Ai Security
Artificial Intelligence
Artificial Intelligence Engineer
AWS
Aws Bedrock
Aws Sagemaker
Cloud Operations
Data Analysis
Data Processing
Engineer
Generative AI
Generative Ai Engineering
Information Technology (IT)
Large Language Models
Llm Orchestration
Machine Learning
Programming
Programming Language
Programming Languages
Rag Architectures
Security
Software Development
Software Engineering
Job Description
Socure is hiring a Staff AI Engineer in New York, NY (onsite) to design and ship agentic workflows and internal productivity tools for AI-driven identity solutions.
Responsibilities
- Partner with business teams (Revenue Ops, Marketing, Finance Ops, Talent Acquisition) to identify manual, high-frequency workflows
- Catalog candidate workflows and rank them by impact, feasibility, and urgency
- Build multi-step, tool-augmented agent workflows that can plan, execute, observe outcomes, and improve iteratively
- Design and implement planner-executor and reflection-based architectures to raise reasoning quality and task reliability
- Create stateful agent systems with human-in-the-loop controls (approval gates, fallback paths, escalation mechanisms)
- Leverage the Agentic AI Foundations platform capabilities, including agent runtime, orchestration, memory, tool registry, guardrails, and observability
- Contribute feedback that influences platform priorities
- Use LLMs, multi-agent frameworks, and orchestration platforms to deliver internal solutions designed to be differentiated rather than off-the-shelf
- Stay current on emerging AI technologies and regulatory frameworks to support secure, compliant, intelligent internal systems
- Identify reusable agent design patterns and contribute them back to Agentic AI Foundations paved paths for enterprise reuse
- Use the evaluation harness and tracing substrate from Agentic AI Foundations for continuous performance assessment, failure-mode analysis, and optimization of speed and accuracy
Requirements
- 8+ years of software engineering experience
- At least 2 years focused on AI/ML systems or LLM-powered applications in production
- Hands-on experience with LLM APIs and at least one agentic framework (LangGraph, CrewAI, or AutoGen)
- Strong Python skills and experience building production-grade backend services, APIs, and data pipelines
- Proven ability to work in ambiguity: define what to build, build it, and measure results
- Experience shipping AI or automation solutions that impacted business operations
- Systems thinking focused on reliability, observability, and maintainability
- Ability to collaborate with non-technical business stakeholders to translate real workflows into technical solutions
Technologies
- Python
- LLM APIs; LLMs
- LangGraph, CrewAI, AutoGen; multi-agent frameworks
- Orchestration platforms; Agentic AI Foundations
- Planner-executor; reflection-based architectures
- Evaluation harness; tracing substrate
- AWS-hosted LLM infrastructure; Bedrock; AgentCore/Strands
- Lambda; SageMaker
- LangSmith; Weights & Biases; Arize
- RAG pipelines; vector databases; knowledge graphs
- Memory and grounding systems
- MCP (Model Context Protocol); function calling
Preferred
- Experience with multi-agent systems, workflow orchestration, or complex tool-use patterns in production
- Familiarity with evaluation frameworks (LangSmith, Weights & Biases, Arize, or custom eval pipelines) for agent reliability, accuracy benchmarking, and 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 (prompt injection prevention, hallucinations mitigation, data protection/privacy)
- Background in regulated industries (fintech, healthcare, government) with standard compliance and security review processes
- Experience with agent skill abstraction and structured tool integration via MCP or function calling-like protocols
- Experience with AWS-hosted LLM infrastructure (Bedrock, AgentCore/Strands, Lambda, SageMaker) or equivalent cloud ML services
Compensation
- $220,000 - $290,000 per year