Salary
💰 $160,000 - $210,000 per year
Tech Stack
AWSCloudDistributed SystemsDockerGoogle Cloud PlatformKubernetesMicroservicesPythonReactTypeScript
About the role
- Architect and implement end-to-end solutions that embed large language models into core product
- Design retrieval-augmented generation workflows and implement RAG pipelines to ground LLMs in domain-specific data
- Integrate and optimize vector databases or embedding stores
- Prototype prompts and integrations, implement backend deployment and monitoring for ML features
- Ensure AI outputs are accurate, safe, and useful; blend model outputs with deterministic logic
- Design infrastructure to support AI features at scale; collaborate with infra/DevOps on microservices, job queues, caching, and monitoring
- Define measurable success criteria and build evaluation pipelines including automated tests and human-in-the-loop reviews
- Partner with Product, Design, and domain experts; mentor engineers and lead internal knowledge sharing
Requirements
- 5+ years of software engineering experience, including 1+ year building AI/ML-powered features in production
- Strong coding ability in backend languages (Python preferred) and experience with system design for cloud-based services
- Hands-on experience integrating LLM APIs or open-source NLP models into live applications
- Solid understanding of distributed systems, API design, and asynchronous programming
- Familiarity with cloud platforms (AWS or GCP), containers (Docker), and orchestration (Kubernetes)
- Practical experience with retrieval-augmented generation, embeddings, and vector databases
- Ability to define and monitor evaluation metrics for AI outputs