We're working with an early-stage AI start-up that's building a no-code platform for custom AI applications. They move fast, iterate quickly, and are looking for someone who is a self-starter, driven and willing to put in the hard work to buidling something together with the team.
You'll be responsible for building reusable, configurable, and scalable LLM components to power their no-code platform, working with the team to implement advanced workflows and monitoring for real-world business applications.
Responsibilities:
- Develop and optimize backend systems for LLM workflow orchestration (retrieval, chaining, evaluation, memory).
- Implement reusable components (e.g., retrieval nodes, validation agents, evaluators) to power the no-code platform.
- Integrate and manage third-party models (e.g., OpenAI, Anthropic, AWS Bedrock, open-source models).
- Develop and maintain multi-agent and tool-augmented AI workflows for common enterprise use cases.
- Work on RAG pipelines, contextual memory management, and prompt engineering best practices.
- Collaborate with front-end and platform engineers to support the no-code interface.
- Conduct systematic evaluations and performance tracking of LLM applications in production.
- Stay updated with emerging GenAI and agentic framework trends.
Requirements:
- Bachelor's degree in Computer Science, AI/ML Engineering, or equivalent experience with about 2-4 years relevant working experience.
- Strong Python programming skills with experience in LangChain, FastAPI, or equivalent frameworks.
- Experience in building production-grade RAG applications and integrating with APIs.
- Familiarity with databases (e.g., PostgreSQL, MongoDB, Redis).
- Experience with cloud platforms (primary: AWS; secondary: Azure, GCP).
- Understanding of LLM architecture and practical applications.