Implement Sophisticated AI Agents: Design, build, and deploy complex AI agents using LangChain and LangGraph. You will own the core logic that automates intricate decision-making within the claims lifecycle.
Master Prompt & Context Engineering: Design, test, and refine complex prompts and contextual data frameworks to ensure our AI agents perform with maximum accuracy, efficiency, and reliability.
Lead AI Research & Innovation: Stay at the bleeding edge of AI. You’ll be responsible for identifying, prototyping, and integrating the latest foundational models, RAG techniques, and agentic frameworks to solve unique business challenges.
Build for Production Scale on GCP: Engineer and operate our AI systems in a scalable, reliable production environment on Google Cloud Platform. Your work will directly impact millions of users.
Champion MLOps for Agentic Systems: Establish and lead best practices for the reliability, versioning, monitoring, and observability of our AI agents, using tools like Langfuse to ensure production-grade performance.
Collaborate to Deliver Impact: Partner closely with product leaders, data scientists, and other engineers to translate business needs into technical reality, ensuring our AI solutions are both innovative and effective.
Champion modern software development practices by actively using AI code-assist tools (e.g., Gemini code assists, Github Copilot, Claude code) to accelerate development cycles, generate documentation, improve code quality, testing, and monitoring & observability practices.
Build, manage, and mentor a cross-functional team of software, quality, and reliability engineers, fostering a culture of technical excellence and continuous improvement.
Define and report on key engineering metrics (SLA, SLO, SLI) and ensure compliance with security, quality, and financial operations (DevSecOps, FinOps) best practices.
Collaborate with product managers, architects, SREs and business partners to define technical strategy, create software roadmaps, and make key architectural and design decisions.
Lead troubleshooting efforts to resolve production and customer issues, demonstrating deep technical expertise and problem-solving skills.
Participate and lead agile team activities, including Sprint Planning and Retrospectives, to ensure efficient and predictable delivery.
Lead with a data/metrics driven mindset with a extreme focus towards optimizing and creating efficient solutions.
Drive up-to-date technical documentation including support, end user documentation and run books.
Create and deliver technical presentations to internal and external technical and non-technical stakeholders communicating with clarity and precision, and present complex information in a concise format that is audience appropriate.
Requirements
Bachelor's degree or equivalent experience
7+ years in software engineering, with a strong track record of technical leadership and shipping complex, scalable systems.
2+ years in a dedicated AI/ML role, with hands-on experience in model integration, MLOps, and applying AI to solve business problems.
1+ years of direct experience architecting and building solutions with LangChain, LangGraph, or similar agentic AI frameworks.
2+ years of in-depth experience with Google Cloud Platform (GCP), specifically its AI/ML services (Vertex AI, etc.).
3+ years of proven experience leveraging Kubernetes workloads.
Proficiency in Python, JavaScript/TypeScript and/or Java and working knowledge of a modern front-end framework (Angular, React, or Vue) to collaborate effectively with UI teams.
Hands-on experience with LLM observability tools like Langfuse for monitoring and debugging agentic workflows.
Tech Stack
Angular
Cloud
Google Cloud Platform
Java
JavaScript
Kubernetes
Python
React
TypeScript
Vue.js
Benefits
comprehensive compensation and healthcare packages
401k matching
paid time off
organizational growth potential through our online learning platform with guided career tracks