Back to jobs

Backend Engineer

Loora
Tel Aviv (Hybrid)Full-time
AI tools:LiteLLMLangChainGuidanceInstructor

Upload your resume once and Scout applies for you

Apply with Scout
Share this job:LinkedInXSave image

You’ll build backend services for Loora’s AI-powered language learning platform, including systems that support real-time conversations and audio and text processing. The role focuses on scalable, low-latency architecture and production reliability, in collaboration with AI/ML, mobile, DevOps, and product teams.

  • Full-time
  • Hybrid
  • 7+ years

Skills and expertise

PythonFastAPIPydanticREST and gRPC APIsAWSKubernetesPostgreSQLKafka

Key responsibilities

  • Design and maintain backend services and APIs for AI-driven conversational experiences.
  • Build asynchronous Python applications for real-time audio and text processing at scale.
  • Improve system architecture, performance, fault tolerance, and deployment reliability.

How this job compares

Compared with 1,635 open senior engineering jobs on November 21, 2026.

Similar open jobs
We Love AI Jobs lists 1,635 open senior engineering jobs at 344 companies.
Remote work
This job is hybrid. 271 of the 1,635 senior engineering jobs (17%) are remote.
AI in this role
Medium. The role uses AI tools and works with AI systems as a regular part of the job. The backend platform powers real-time AI conversations, and the engineer will integrate mobile and web clients with the AI backend. The role focuses on backend systems rather than building or training models.

Full description

Loora is on a mission to revolutionize education and break down language barriers with its cutting-edge AI, building the first-ever personal AI English tutor. Loora offers its users an AI tutor that is always available to talk about whatever they want, give immediate feedback on English skills, and guide them on their journey to fluency.

We are looking for a Backend Engineer to drive the architecture and development of our AI-powered language learning platform. In this role, you will design and implement backend systems that directly impact millions of learners worldwide. You will architect scalable services that power real-time AI conversations, ensuring low-latency performance and reliability while building the foundation for our next generation of language learning features.

What You’ll Do

• Design, develop, and maintain high-performance backend services and APIs (REST and gRPC) that power AI-driven conversational experiences.

• Build and optimize asynchronous Python applications capable of handling real-time audio/text processing at scale.

• Ensure seamless, low-latency integration between mobile and web clients and our AI backend platform.

• Drive technical decisions on system architecture, focusing on low latency and fault-tolerance.

• Collaborate with AI/ML, mobile, DevOps, and product teams to deliver end-to-end solutions that delight our users.

• Work within CI/CD workflows to ensure smooth deployments and maintain high code quality standards.

• Optimize system performance and resource utilization while maintaining reliability SLAs for our growing user base.

What We're Looking For

• Minimum of 7 years of experience designing and developing scalable, distributed backend systems in one or more modern programming languages (Python is a plus).

• Deep expertise in Python concurrency and execution models (WSGI, ASGI, asyncio, multiprocessing, threading, GIL).

• Proven track record building production-ready asynchronous Python applications serving high-volume traffic.

• Strong experience with Pydantic and FastAPI in production environments.

• Expertise in designing and implementing RESTful APIs and gRPC services with strong emphasis on versioning strategies and backward/forward compatibility.

• Demonstrated ability to solve complex performance, scalability, and workload distribution challenges.

• Proficiency with relational and non-relational database solutions (PostgreSQL, Redis, DynamoDB, MongoDB), including query optimization and data modeling.

• Experience with event-driven architectures and message queuing systems (Kafka, RabbitMQ, AWS SQS).

• Hands-on experience with Docker, understanding of CI/CD pipelines and methodologies, and working in Kubernetes/AWS-based deployments.

• Strong proficiency with AWS cloud services and cloud-native architectures.

• Understanding of observability practices (distributed tracing, metrics, logging) and experience with monitoring tools.

Even better if you have:

• Proficiency in additional backend programming languages (Go, Rust, Java, Scala, Kotlin).

• Experience with audio/video streaming protocols and real-time communication systems.

• Experience with dataframe libraries (Pandas, Polars, Daft) for data processing and analytics.

• Familiarity with LLM integration libraries (LiteLLM, LangChain, Guidance, Instructor) and AI model serving frameworks.

• Background in building data-driven applications, pipelines, or ETL processes using frameworks like Apache Spark / Flink and orchestration tools such as Airflow or Dagster.

• Contributions to OSS projects on GitHub.

Upload your resume once and Scout applies for you

Apply with Scout

Similar jobs