3+ years experience
Build and deploy AI powered features across our products. This role focuses on LLM driven applications, RAG systems, and production grade integrations, not pure research.
- Build AI powered product features (copilots, assistants, automation workflows)
- Design and implement RAG pipelines (data ingestion, chunking, embeddings, retrieval)
- Integrate LLM APIs (OpenAI, Anthropic, etc.) into web and mobile applications
- Develop backend APIs and infrastructure to support AI workflows
- Optimize for latency, cost, and response quality
- Implement logging, monitoring, and evaluation for AI outputs
- Work closely with product and design to shape AI native user experiences
- 3+ years in software engineering (Python required)
- Experience building with LLMs in production (not just demos)
- Strong understanding of RAG, embeddings, and vector databases
- Experience with frameworks like LangChain, LlamaIndex, or similar
- Solid backend fundamentals (APIs, async processing, data pipelines)
- Familiarity with cloud environments (AWS, GCP, or Azure)
- Experience with fine tuning or model optimization
- Knowledge of evaluation frameworks and guardrails
- Frontend experience (React or Next.js) for AI feature integration
- Experience with real time or streaming AI applications
PythonLangChainLlamaIndexVector DBsOpenAIAnthropic
