About this Role
As a Software Engineer specializing in AI retrieval, you will design, implement, and optimize AI retrieval systems that power our platform. Collaborating with data scientists, product managers, and engineers, you will ensure seamless integration of AI models into applications, delivering fast and accurate results. A strong foundation in software engineering, AI, and machine learning is essential.
Your responsibilities:
Design and implement AI retrieval systems: Develop and maintain core algorithms and services for efficient content search and retrieval.Optimize performance: Ensure systems are scalable, high-performing, and capable of handling large data volumes and requests.Collaborate with cross-functional teams: Work closely with data scientists, product managers, and engineers to understand requirements and deliver quality solutions.Code quality and best practices: Write clean, maintainable, and well-documented code following best practices.Testing and validation: Develop unit and integration tests to ensure system reliability and accuracy.API development: Build and maintain REST and GraphQL APIs using frameworks like FastAPI and Flask to expose AI retrieval capabilities.Streaming and cancelable endpoints: Implement features supporting real-time responses and interactive use cases.Continuous improvement: Stay updated with AI and software engineering advancements to enhance systems and processes.️Is this you?
- Proficient in Python: Strong understanding of data types, string manipulation, type casting, and conversions.
- Functions: Experienced with calling functions, using default/variable arguments, and lambda functions.
- Virtual environments: Familiar with tools like venv, virtualenv, pipenv, and poetry.
- File handling: Skilled in reading, writing, and manipulating files in Python.
- Error handling: Expert in managing exceptions for robust code.
- Data models: Knowledgeable in designing and using data models.
- Logging and context managers: Proficient in maintaining code clarity and traceability.
- OOP concepts: Experienced with inheritance, method overriding, and Python's magic methods.
- Code formatting: Adheres to standards using black, isort, flake8, pylint.
- Testing: Background in unit testing, mocking, and integration testing.
- Versioning: Familiar with semantic versioning and changelogs.
- Data structures: Proficient with stacks, queues, priority queues (collections).
- Functional programming: Experienced with map, filter, reduce, generators, decorators.
- Async programming: Skilled in asyncio, aiohttp, async generators, wait_for.
- Concurrency: Understand threading vs multiprocessing and their trade-offs.
- Profiling: Proficient with tracemalloc, cProfile for performance optimization.
- API development: Experienced with REST and GraphQL APIs via FastAPI, Flask.
- Streaming and cancelable endpoints: Capable of implementing real-time features.
Preferred skills and experience
- Machine learning frameworks: TensorFlow, PyTorch, scikit-learn.
- NLP tools: spaCy, NLTK.
- Distributed systems: Kubernetes, Docker.
- Cloud platforms: AWS, GCP, Azure.
- Open source contributions: Personal projects or contributions.
Benefits & perks (US Full-time employees):
- Generous PTO and holidays
- Medical, dental, vision coverage
- Paid parental leave (12 weeks)
- Fertility and family planning support
- Early cancer detection via Galleri
- FSA and HSA options
- Work-life stipends (home setup, wellness, learning)
- Company off-sites
- Competitive compensation, stock options, 401k
Writer is an equal-opportunity employer committed to diversity. We consider qualified applicants regardless of race, gender, age, disability, or other protected statuses. By applying, you agree to our Global Candidate Privacy Notice.
#J-18808-Ljbffr