Get more replies from employers
Send a job-specific resume in minutes.
Lyzr AI in New Jersey is seeking a Staff Core Engineer to own end-to-end complex systems on the Platform team, setting technical direction for core agent architecture including orchestration, memory, RAG, and guardrails.
This hands-on leadership role requires designing scalable, reliable distributed systems, shaping cloud, CI/CD, monitoring, and tracing practices, and mentoring engineers across the team.
Lyzr is the full-stack agent infrastructure platform that lets enterprises build, govern, and deploy a secure, autonomous AI workforce. Where most companies run a handful of copilots, Lyzr is the layer that lets them run an entire AI workforce in production — governed, reliable, and at scale.
Backed by Accenture and trusted across banking, insurance, sales, marketing, HR, and customer service, Lyzr offers a “third way” for enterprise AI: the flexibility of an open platform combined with the security of a managed platform, deployed inside the customer’s own environment for full data privacy and IP ownership.
The Platform team builds the engine underneath all of it: the agent framework and its core components — orchestration, tool execution, agent memory, RAG, Text2SQL, guardrails, and observability.
As a Staff Core Engineer on the Platform team, you own entire complex systems end-to-end. You set the technical direction for our core agent architecture — orchestration, tool execution, memory, RAG, Text2SQL, and guardrails — and you push the platform forward with new ideas and a research-driven mindset.
This is a hands-on technical leadership role. You’ll lead design reviews, set quality standards, mentor engineers across the team, and make the architectural calls that determine how reliably our AI workforce runs in production at scale.
Design and own entire complex systems end-to-end, from architecture through production operation
Own the core agent architecture: orchestration, tool execution, agent memory, RAG, Text2SQL, and guardrails
Drive scalability and reliability across distributed systems serving enterprise agent workloads
Establish robust cloud, CI/CD, monitoring, logging, and tracing practices for the platform
Bring a research-driven mindset — evaluate emerging techniques and turn promising ideas into shipped capabilities
Lead design reviews, set engineering quality standards, and mentor senior and junior engineers
Partner with product and other teams to translate ambiguous problems into durable technical strategy
Demonstrated track record of building impactful, large-scale systems end-to-end
Deep expertise in distributed systems and scalable architectures
Strong, current Python expertise and excellent system design instincts
Hands‑on experience operating production systems on the cloud with mature CI/CD, monitoring, logging, and tracing
Experience with one or more core agent components: orchestration, tool execution, memory, RAG, Text2SQL, or guardrails
Proven ability to mentor engineers, lead design reviews, and raise the bar for quality across a team
Go for performance‑critical components
Published research or open‑source contributions in LLM/agent infrastructure
Experience building guardrails, safety, or responsible‑AI systems
Prior experience in an enterprise or regulated environment (e.g., banking, insurance)