Senior Staff Engineer

Summary

Join our dynamic and rapidly growing Digital Product Engineering company as we build innovative products and services. We are a global team of 19,000+ experts across 33 countries. This role requires strong programming skills in Python and Typescript/React, experience with backend web services, cloud services, containerization, CI/CD, and application monitoring. Experience with vectors, embeddings, LLM concepts, and MLOps/LLMOps tools is also essential. Data engineering experience is a key requirement. Prior experience building a user-facing GenAI/LLM application is a plus.

Requirements

• Possess strong programming proficiency in Python (OOP, Async/Await, etc.)
• Demonstrate strong programming proficiency in Typescript/React and have front-end development experience
• Have experience with cloud provider managed services (AWS, Azure) and IaC (Terraform)
• Have experience with containerization and container app deployments (Docker, Kubernetes, etc.)
• Have experience with CI/CD concepts and tooling (Github Actions, Gitlab CI, etc.)
• Have experience with application logging/monitoring (Sentry, ELK stack, Datadog, etc.)
• Possess strong knowledge of service integrations and protocols (REST, streams, web sockets, webhooks)
• Possess strong knowledge of distributed tasks using queues and consumers, pub/sub architecture
• Have previous experience with vectors and embeddings (pgvector, chromadb)
• Have knowledge of LLM RAG/Agent core concepts and fundamentals
• Have previous experience with MLOps/LLMOps tools (Arize Phoenix, LangSmith, MLFlow, W&B, etc.)
• Have data engineering experience (data modeling, data pipelines, event streaming, etc.)
• Must have Skills: React (Strong), Python (Expert), Docker (Strong), AWS

Responsibilities

• Build backend web services (FastAPI or similar)
• Develop and deploy containerized applications using Docker and Kubernetes
• Implement CI/CD pipelines using tools like Github Actions or Gitlab CI
• Implement application logging and monitoring using tools like Sentry, ELK stack, Datadog, etc
• Develop and maintain service integrations using REST, streams, web sockets, and webhooks
• Design and implement distributed task processing using queues, consumers, and pub/sub architecture
• Work with vectors and embeddings using tools like pgvector and chromadb
• Apply knowledge of LLM RAG/Agent core concepts and fundamentals
• Utilize MLOps/LLMOps tools such as Arize Phoenix, LangSmith, MLFlow, W&B, etc
• Perform data engineering tasks including data modeling, data pipelines, and event streaming

Preferred Qualifications

Previous experience building a user-facing GenAI/LLM software application