GenAI Engineer
Think you’re the right fit for our GenAI Engineer role?
Email your resume to careers@neolumin.com.
We’d love to hear from you.
Job Description
We’re seeking a skilled Backend Engineer to develop a web API for a GenAI web application. The ideal candidate should have a strong foundation in Python, experience with vector databases, and a solid understanding of LLMs. Knowledge of prompt engineering and LLM optimization for embeddings and inference is essential. A cloud-first mindset is required to ensure the application is both cost-effective and scalable.
Core Skills
- Proficient in Python and frameworks such as Flask, Django, LlamaIndex, and LangChain.
- Experience with vector databases (in-memory and persistent).
- Familiarity with LLMs, including their best use cases (e.g., embeddings vs. inference) and optimization for accuracy, speed, and cost.
- Understanding of prompt engineering strategies for effective model utilization.
- Cloud-native application development and deployment.
- Familiarity with OAuth2, JWT, or similar frameworks.
Desirable Skills
- Experience with scalable architecture design.
- Knowledge of cost optimization techniques in cloud environments.
- Hands-on experience with containerization (Docker) and orchestration (Kubernetes).
- Familiarity with microservices and serverless architecture.
- Ability to execute performance tuning and monitoring, particularly for handling large datasets and ensuring low latency in semantic search queries.
Expectations
- The engineer should have expertise in working with large datasets, embedding models, vector databases, semantic search, API development, and API security.
- The project should be approached with a focus on scalability, performance, cost-efficiency, security, and continuous improvement.
