AI/ML Engineer, Senior — United States

About the Company

Nivoda is a digital marketplace and operating platform for the global jewellery industry. It connects diamond and gemstone suppliers directly with jewellery retailers across more than 70 countries, making trading more accessible, transparent, and efficient. The platform supports more than $300 million in annual transactions within a global jewellery industry valued at over $350 billion.

Nivoda's mission is to simplify diamond and gemstone trading by providing jewellery businesses of all sizes with access to transparent pricing and a more efficient way to buy and sell worldwide. Following its continued growth, the company is expanding its technology and AI capabilities.

About the Role

Nivoda is seeking a Senior AI/ML Engineer to join its Discovery Pod, the team responsible for developing the search, ranking, and recommendation systems that help buyers find diamonds and gemstones across its marketplace.

This role involves building production-grade information retrieval and applied machine learning systems, including embedding-based retrieval, learning-to-rank, conversational search, and image-based product discovery. You will own models throughout their lifecycle, from feature development and training to evaluation, deployment, and monitoring. The role also involves designing systems that work across Nivoda's marketplace and independently branded jeweller storefronts.

Key Responsibilities

Core Search and Ranking Systems

• Build and operate search infrastructure using Elasticsearch, OpenSearch, Vespa, or vector-search technologies to support ranking and multi-modal search across Nivoda's marketplace.

• Design multi-tenant, configurable ranking and recommendation systems that serve Nivoda's marketplace and individually branded jeweller storefronts through Feeds without maintaining separate codebases.

• Develop embedding-based retrieval and ranking capabilities as part of the Discovery Pod's new search infrastructure.

Multi-Modal AI

• Build and improve contextual search and the planned conversational assistant using prompt design and retrieval-augmented approaches.

• Handle zero-result searches and search trade-offs gracefully, avoiding misleading or incorrect responses.

• Develop image-to-attribute and image-to-product-match pipelines using image embeddings for image-upload search.

• Design recovery paths and confirmation steps for probabilistic systems, particularly before high-stakes actions such as generating manufacturing quotes from interpreted images.

Experimentation and Quality

• Define and conduct search- and ranking-specific evaluations using offline ranking metrics and interleaving experiments.

• Assess whether ranking changes improve search quality rather than simply producing different results.

• Evaluate and stress-test foundation models and LLM outputs as part of the engineering process.

Production Machine Learning

• Own the complete lifecycle of ranking and recommendation models, including feature development, training, evaluation, deployment, and monitoring.

• Apply learning-to-rank, embedding-based retrieval, and collaborative filtering techniques.

• Design and optimize low-latency, real-time model-serving systems that maintain responsive search experiences under production load.

• Use AI coding agents to build ML infrastructure and pipelines, supported by rigorous evaluation and testing systems that identify ranking and retrieval issues.

Required Qualifications

• Five to ten years of professional experience.

• Experience building or operating information retrieval infrastructure using Elasticsearch, OpenSearch, Vespa, or vector-search databases such as pgvector, Pinecone, or Weaviate.

• Hands-on experience with applied machine learning for ranking and recommendations, including learning-to-rank, embedding-based retrieval, and collaborative filtering.

• Ability to manage the full model lifecycle, including features, training, evaluation, deployment, and monitoring.

• Production experience building applications with NLP and large language models, including prompt design and retrieval-augmented approaches.

• Experience handling zero-result searches and trade-off scenarios in LLM-powered applications.

• Experience building and optimizing low-latency, real-time model-serving systems under production load.

• Knowledge of search- and ranking-specific evaluation methods, including offline ranking metrics and interleaving experiments.

• Hands-on experience building with foundation models and LLMs, including evaluating and stress-testing model outputs.

• Ability to design graceful failure and recovery mechanisms for probabilistic systems.

• Comfort using AI coding agents to develop ML infrastructure and pipelines, with strong evaluation and testing practices.

Preferred Qualifications

• Knowledge of computer vision fundamentals, particularly image embeddings.

• Experience developing image-to-attribute or image-to-product-match pipelines.

• Experience designing multi-tenant, configurable systems that support different customer requirements without separate codebases.

• Experience building conversational or assistant-style search products.

• Background in search, ranking, or recommendation teams at marketplace or e-commerce companies.

Technology Stack

• Search: OpenSearch, PostgreSQL change data capture (CDC), Spark, EMR, and AWS Glue.

• Core Database and Warehouse: PostgreSQL and Snowflake, with dbt-managed medallion architecture across raw, curated, and presentation layers.

• Backend: TypeScript, Node.js, GraphQL API gateway, Nx monorepo, and PNPM.

• Authentication: Keycloak.

• Single Sign-On: Okta.

• CI/CD: Jenkins and GitOps.

• Cloud: AWS, including EMR, Glue, DMS, and Kubernetes-based deployments.

• Observability: Grafana for logs and traces.

Company Culture and Benefits

Nivoda offers a collaborative, high-growth environment built around ownership, empowerment, and continuous learning. Team members have opportunities to take responsibility from day one, work on complex technical challenges, and contribute to the company's continued expansion.

• Flexible working hours.

• Remote-first work culture.

• Opportunities for professional growth and learning.

• Unlimited holiday allowance.

• Opportunity to join during a period of significant company expansion.

Salary and Position Details

• Annual Salary: $200,000–$280,000.

• Job Title: Senior AI/ML Engineer.

• Team: Discovery Pod.

• Location: New York City or Boston, United States.

• Work Arrangement: Remote-first.

Equal Employment Opportunity

Nivoda is an equal opportunity employer committed to building a diverse and inclusive team. The company welcomes applicants from all backgrounds, regardless of race, gender, age, religion, sexual orientation, disability, or any other characteristic protected by law. Candidates are encouraged to apply even if they do not meet every listed requirement.