What you’ll do

• Take ownership of features from idea to production: plan, build, launch, and iterate with clear milestones.
• Develop and ship GenAI features, including retrieval-augmented generation (RAG), grounding/context engineering, orchestration, and guardrails.
• Build data pipelines to ingest, clean, transform, and index content (batch + streaming) for reliable retrieval and analytics.
• Design and maintain APIs and services that are simple, stable, and scalable.
• Strengthen reliability through tests, metrics, observability, and safe rollout practices.
• Ensure compliance with security, privacy, and multi-tenant requirements.
• Collaborate cross-functionally with Product and Design to scope, validate, and refine user-facing experiences.
• Raise the technical bar through code reviews, design docs, and mentoring.

•  5–8 years of experience building production backend or platform software.
• Proven track record of shipping applied AI features in real products (e.g., LLMs, RAG, fine-tuning, or tools).
• Strong data pipeline skills: preprocessing, schema design, indexing/vector search, and monitoring.
• Fluency in at least one of Node.js, Kotlin, or Python, with the ability to learn others.
• Familiarity with cloud environments (AWS/GCP), containers, CI/CD, and infrastructure-as-code.
• Strong product sense with the ability to simplify scope, make trade-offs, and explain decisions clearly.
• Autonomous, outcome-oriented mindset with a bias for action.
• Clear written and verbal communication skills for collaborating in a distributed team.
• Bonus points for knowledge management/search, CMS/DAM, or enterprise integrations.
• Bonus points for LangChain/LlamaIndex, vector DBs, embeddings pipelines, or MCP‑style integrations.
• Bonus points for Experience with evaluation of LLM systems (automatic + human review) and safety practices.