Senior Software Engineer Ii, AI Labs & Foundations

Instacart Instacart · Consumer · United States · Remote · Software Engineering

Senior Software Engineer on Instacart's AI Labs & Foundations team, responsible for designing, building, and operating high-scale production AI systems and agentic experiences like Cart Assistant and voice AI. This role involves integrating foundation models, applying techniques like RAG and vector search, and owning projects end-to-end, impacting millions of customers.

What you'd actually do

  1. Design, build, and operate production AI-powered systems and agentic experiences (including Cart Assistant and voice AI) that directly impact how millions of customers shop.
  2. Build foundational systems for cutting-edge AI experiences, ranging from embedding infrastructure and voice AI pipelines, to client facing components and integrations, by prototyping bold ideas and productizing what works.
  3. Integrate foundation models via APIs and open-source frameworks; apply techniques like retrieval-augmented generation and vector search where appropriate.
  4. Own projects end-to-end: requirements, technical design, implementation, testing, deployment, observability, and iterative improvement focused on reliability, latency, and cost efficiency.
  5. Collaborate with cross-functional partners in product, design, data science, and infrastructure to ship AI features end-to-end.

Skills

Required

  • Proven senior software engineer who has built, shipped, and operated production systems at scale.
  • Hands-on experience with AI or ML in production.
  • Experience owning services end-to-end, including CI/CD, automated testing, observability (logging, metrics, tracing), and on-call participation.
  • Strong communicator who partners well across disciplines.

Nice to have

  • 5 to 8+ years of industry experience.
  • A track record of 0-to-1 work taking unconventional ideas from prototype through rapid iteration to production.
  • Experience building conversational agents, multi-turn dialogue systems, or agentic LLM applications.
  • Experience with STT/TTS or natural language interfaces, LLM fine tuning, ML transfer learning, model training and the vocabulary of measurement of model performance.
  • Experience with embedding systems, vector search, or retrieval-augmented generation (RAG) with vector databases (e.g., Pinecone, Weaviate, FAISS, or Elasticsearch).
  • Experience with cloud platforms (AWS or GCP), containers (Docker), and orchestration (Kubernetes).
  • Experience with event-driven or distributed systems (e.g., Kafka).
  • Demonstrated mentorship and technical leadership within cross-functional teams.

What the JD emphasized

  • built, shipped, and operated production systems at scale
  • shipped LLM-powered features or integrated foundation model APIs into a live product
  • Experience building conversational agents, multi-turn dialogue systems, or agentic LLM applications
  • Experience with embedding systems, vector search, or retrieval-augmented generation (RAG) with vector databases

Other signals

  • building foundational systems for AI
  • shipping LLM-powered features
  • operating production AI systems