Staff Full-Stack Engineer, AI Engineering
TWG AI · New York, NY · 1 mo ago
On-siteEngineeringFull-time
Key Responsibilities
- Design, build, and operate agent-based software that executes multi-step tasks with tools, memory, and stateful workflows using LangGraph or equivalent frameworks
- Build and maintain evaluation pipelines for LLM and agent quality: offline eval suites, regression tests, tool-call and trajectory scoring, and the dashboards and tooling that make results actionable
- Lead development of React frontends with clean component architecture, sensible state management, and real performance work
- Design and maintain backend services, REST APIs, and data models in Java (Spring Boot) and Python
- Contribute to system design across multi-tenant infrastructure, auth, and async messaging
- Support features for our iOS apps, including UI, networking, push notifications, and release management
- Drive code quality, testing discipline, and engineering standards
- Mentor junior engineers and raise the bar through code review and design feedback
Requirements
- 8+ years building production software at scale
- Hands-on experience building real LLM and agent applications, not demos. You've designed tool interfaces, orchestrated multi-step workflows, handled failure modes in agent loops, and shipped something users depend on
- Direct experience with agent evaluation: building golden datasets, running offline evals, scoring tool calls and trajectories, and using eval results to drive prompt, model, and architecture changes
- Familiarity with frameworks like Braintrust, LangSmith, Inspect, or comparable custom harnesses
- Strong React, including state management, component design, and performance
- Strong Java with Spring Boot, plus working proficiency in Python
- Relational database design (PostgreSQL preferred)
- Comfort with distributed systems, async messaging, and modern service architecture
- Cloud infrastructure (AWS, GCP, or Azure) and CI/CD
- Bachelor's degree in CS, Engineering, or equivalent practical experience
Preferred Qualifications
- Experience with LangGraph specifically, or having built comparable orchestration from scratch
- iOS development with Swift and SwiftUI, including App Store release experience and APNs
- Multi-provider LLM work (Anthropic, OpenAI, Google, xAI) and MCP servers or clients
- Redis Streams or similar async messaging at production scale
- Multi-tenant SaaS with non-trivial RBAC and auth
- On-device ML on iOS (CoreML, NLContextualEmbedding) or audio pipelines (Whisper, TTS)
- Prior experience working with Palantir Foundry
Benefits
- Work on real-world AI applications with high-impact clients
- Collaborate with world-class data scientists, engineers, and product leaders
- Flat org structure, high trust, high autonomy
- Competitive salary + performance-based incentives
Pay
The target base pay for this position is $290,000-$300,000. A bonus will be provided as part of the compensation package, in addition to the full range of medical, financial, and/or other benefits.
Schedule
This is an onsite position preferred to be located in Santa Monica, CA, or New York, NY. Relocation support can be provided to the right candidates.