2 months ago
Remote, IndiaSenior
Responsibilities
- Design and build AI/LLM data pipelines for training, inference, evaluation, embeddings, and retrieval workloads.
- Build production-grade RAG systems covering ingestion, chunking, embedding generation, indexing, retrieval, reranking, and context construction.
- Develop LLM applications with structured outputs, function and tool calling, and agentic workflows.
- Build and optimize semantic search and vector retrieval systems.
- Create frameworks for LLM evaluation, monitoring, tracing, quality measurement, latency analysis, and cost optimization.
- Design scalable batch and streaming pipelines using Databricks, Apache Spark, Delta Lake, Snowflake, and Airflow.
- Build data products and platforms that expose structured and unstructured enterprise data to AI applications.
- Develop reliable ETL/ELT pipelines and optimize distributed workloads for performance and cost.
- Establish data quality, governance, lineage, security, and observability practices.
- Partner with ML and application engineering teams to productionize AI prototypes.
Requirements
- 5+ years of experience in data engineering, software engineering, distributed systems, or a related field.
- Strong programming skills in Python and/or Scala or Java, plus advanced SQL.
- Hands-on experience with Databricks, Snowflake, Apache Spark, Delta Lake, and Airflow.
- Experience with cloud data platforms such as Snowflake and/or Databricks.
- Practical experience building applications using LLMs or Generative AI.
- Strong understanding of RAG architectures, embeddings, vector databases, semantic search, and retrieval systems.
- Familiarity with prompting, structured outputs, tool calling, and model evaluation.
- Experience designing scalable, reliable, and observable production data systems.
- Preferred experience with large-scale data platforms, distributed processing, real-time and streaming architectures, Kafka, Spark Structured Streaming, low-latency pipelines, and event-driven architectures.
- Preferred experience with complex ETL/ELT orchestration, Spark and Databricks optimization, batch and real-time AI/ML platforms, LLM evaluation frameworks, evaluation datasets, AI observability, and tracing.
- Preferred experience with LangGraph, LangChain, LlamaIndex, Qdrant, Pinecone, Weaviate, Databricks Vector Search, MLflow, Unity Catalog, Databricks Mosaic AI, and model-serving platforms.
- Strong understanding of distributed systems, cloud architecture, APIs, CI/CD, production operations, data quality, lineage, governance, and data/AI observability frameworks.
Benefits
- 100% remote across India, with the ability to work from almost anywhere for up to 20 days per year.
- Company-paid therapy sessions through SpringHealth and a company-paid Headspace subscription.
- Annual company-wide week off.
- Paid parental leave, generous paid vacation, and birthday time off.
- Paid volunteer time, development dollars, leadership development, and access to thousands of on-demand e-learning courses.
- Travel discounts, employee resource groups, quarterly team offsites, tax optimization options, health insurance, and a pension fund.
- Schedule flexibility for global collaboration, with occasional communications outside regular working hours.
Tech Stack
Categories
AI ApplicationsData Engineering
About OpenTable
OpenTable builds an online restaurant reservations marketplace for diners and reservation, guest management, and operations software for restaurants, sold via subscriptions and per-cover fees. Its consumer apps and integrations power bookings across 70,000+ restaurants worldwide and connect with POS and other hospitality systems. Founded in 1998 and headquartered in San Francisco, OpenTable is part of Booking Holdings.