Overview
Build generative AI applications, retrieval and agents on enterprise data and run them safely in production.
What you'll do
- Design and build of LLM-based applications and agents
- Build retrieval-augmented generation over enterprise data, including vector databases and embedding pipelines
- Design prompts, tools and workflows for agentic use cases
- Build evaluation frameworks, quality metrics and guardrails
- Integrate with enterprise systems through APIs
- Deploy, monitor and manage cost in production
- Work with business owners on use cases and value
What you bring
- Hands-on experience shipping LLM or generative AI solutions
- Python and modern LLM frameworks such as LangChain or LangGraph
- Model APIs and managed services such as OpenAI, Anthropic, Azure OpenAI or Amazon Bedrock
- RAG patterns, embeddings and vector databases
- Cloud platforms such as AWS, Azure or GCP, plus API design and integration
- Evaluation and testing of model outputs
- Awareness of security, privacy and responsible AI practices
You don't need every item on this list. If most of it fits, send your CV.
Nice to have
- Regulated-industry experience
- MLOps or LLMOps tooling
- Fine-tuning or small-model experience
- Knowledge graphs
- Front-end or full-stack skills
- Cloud AI certifications