Staff Software Engineer - AI

What you will do

AI/ML Architecture & Systems Design

• Architect, build, and optimize recommendation engines, personalization systems, and classification models for GTM automation
• Design and implement multi-LLM architectures combining OpenAI, Claude, and Databricks models for intelligent decisioning and reasoning
• Build, train, and evaluate models
• Deploy and serve models using FastAPI, Kubernetes, and async microservices, with observability built in
• Develop MLOps workflows for fine-tuning, retraining, model versioning, and automated evaluation

Data Engineering & Model Pipelines

• Design medallion data architectures (Bronze/Silver/Gold) using Databricks Delta Live Tables and CDC patterns
• Build real-time and batch data pipelines leveraging Kafka and Databricks for high-volume model inputs
• Develop and maintain embedding systems and matrix factorization-based recommendation frameworks for personalization and ranking
• Implement AI data quality and monitoring frameworks to ensure reliability and trust in model outputs

AI Reliability, Observability & Optimization

• Implement AI observability (LangSmith, Braintrust) to track performance, bias, and drift
• Build fallback and routing systems for multi-model deployments
• Optimize cost and latency through batching, caching, and adaptive model selection

Technical Leadership & Collaboration

• Lead design reviews and guide architecture for AI/ML-driven systems
• Mentor engineers on LLM integration, MLOps, and recommendation systems
• Collaborate closely with product and GTM partners to translate business goals into AI-driven automation

What you will need

• 7+ years of software engineering experience, including 3+ years building production ML systems
• Expertise in recommendation engines, matrix factorization, and personalization models
• Deep experience integrating LLMs (OpenAI, Claude, etc.) into production applications
• Hands-on experience training, evaluating, and deploying models in Databricks notebooks and Spark pipelines
• Experience with MLOps tooling for off-the-shelf models like XGBoost, CatBoost, or LightGBM
• Strong background in data engineering (Kafka, Spark, Databricks, PostgreSQL)
• Proven ability to architect scalable AI systems and lead end-to-end deployment

Preferred Skills

• Familiarity with LangChain, LangSmith, and vector databases
• Deep understanding of multi-LLM coordination patterns, dynamic prompt routing, and evaluation loops
• Experience implementing AI safety, guardrails, and interpretability frameworks
• Experience deploying containerized AI services on Kubernetes
• Solid understanding of feature stores, experiment tracking, and online/offline evaluation