We're partnering with an innovative AI-driven company building next-generation intelligent systems that automate complex workflows, reasoning tasks, and decision-making processes.
We're looking for a hands-on Senior AI Engineer who has experience building and deploying AI products in production, ideally within high-growth startups (Seed, Series A, Series B, or Series C environments). This is an opportunity to help shape core AI architecture, own systems end-to-end, and develop agentic AI capabilities that directly impact the business.
This role is hybrid, requiring 3 days per week onsite in New York City.
What You'll Do
Build Production Agentic AI Systems
- Design, develop, and deploy production-grade AI applications powered by LLMs and autonomous agent architectures
- Build multi-agent systems capable of planning, reasoning, memory management, tool usage, and workflow orchestration
- Develop AI products that move beyond prototypes and operate reliably in real-world production environments
- Design scalable architectures for long-running agent workflows and complex task execution
Own AI Systems End-to-End
- Lead the full lifecycle from concept and architecture through deployment, monitoring, and continuous improvement
- Build APIs, services, data pipelines, agent frameworks, and supporting infrastructure
- Partner closely with Product, Engineering, Design, and Leadership teams to identify high-impact AI opportunities
- Drive technical decisions around model selection, orchestration frameworks, architecture, and deployment strategies
Retrieval, Knowledge & Memory Systems
- Design and implement advanced RAG architectures
- Build long-term memory and context-management systems for AI agents
- Develop integrations with vector databases, knowledge stores, and enterprise data sources
- Improve retrieval quality, agent accuracy, and reasoning performance across workflows
Reliability, Evaluation & Scale
- Build evaluation frameworks and testing pipelines for AI systems
- Establish observability, monitoring, guardrails, and governance for production AI applications
- Improve latency, reliability, scalability, and cost efficiency across AI workloads
- Create processes that allow AI systems to operate safely and effectively at scale
What We're Looking For
Required
- 6+ years of software engineering, machine learning, or AI engineering experience
- Strong Python engineering background with experience building production systems
- Demonstrated experience deploying LLM-powered products used by real customers
- Hands-on experience building multi-agent or agentic AI systems in production
- Experience with frameworks such as LangGraph, LangChain, CrewAI, AutoGen, OpenAI Agents SDK, or similar
- Strong understanding of RAG architectures, retrieval systems, vector databases, and embeddings
- Experience designing distributed systems, APIs, and scalable backend services
- Experience deploying applications on AWS
- Strong systems-thinking mindset and ability to operate in fast-moving startup environments
Highly Preferred
- Experience working at venture-backed startups (Seed, Series A, Series B, or Series C)
- Experience being one of the first AI hires or an early engineering team member
- Proven track record taking AI products from 0→1 and scaling them in production
- Experience building AI infrastructure, orchestration platforms, or developer tooling
- Experience with agent memory, planning, tool calling, MCP, and workflow orchestration
- Experience deploying production systems using Docker, Kubernetes, Terraform, or modern DevOps tooling
- Experience evaluating and benchmarking LLMs and autonomous agents