Senior AI/ML Engineer

Nivoda•Dover, NH

1d•Remote

About The Position

Nivoda is seeking a Senior AI/ML Engineer to join the Discovery Pod. This role will focus on building and running the ranking, recommendation, and search systems that enable buyers to find the right stone or piece in seconds. This is a hands-on role involving information retrieval and applied ML on production infrastructure, including search systems, embedding-based retrieval, learning-to-rank, LLM-powered contextual and conversational search, and image embeddings for photo-based search. The engineer will own models end-to-end, from features and training through evaluation, deployment, and monitoring, with a deep understanding of how probabilistic systems behave and fail being crucial.

Requirements

5-10 years of experience.
Information retrieval infrastructure experience — building or operating real search systems (Elasticsearch/OpenSearch, Vespa, or vector-search databases like pgvector, Pinecone, or Weaviate).
Applied ML for ranking and recommendations, end to end — learning-to-rank, embedding-based retrieval, collaborative filtering — with comfort owning features, training, evaluation, deployment, and monitoring.
NLP and LLM application experience — production experience building on top of language models, including prompt design, retrieval-augmented approaches, and handling zero-result and tradeoff scenarios gracefully.
Low-latency serving experience — built and optimized real-time model-serving systems under production load.
Specialized evaluation skills for search and ranking quality, distinct from general growth experimentation — offline ranking metrics, interleaving experiments, and judging whether a ranking change is actually better versus just different.
Direct, hands-on experience building with foundation models and LLMs as an engineering material — prompt design, retrieval-augmented approaches, and critically, evaluating and stress-testing model output rather than trusting it by default.
Experience designing for graceful failure in probabilistic systems — knowing when a model is confidently wrong and building the product around that reality.
Comfort using AI coding agents to build ML infrastructure and pipelines, paired with strong evaluation and testing discipline.

Nice To Haves

Computer vision fundamentals, specifically image embeddings — experience building image-to-attribute or image-to-product-match pipelines.
Multi-tenant, configurable system design experience — building systems that behave differently per tenant without forking the codebase.
Experience building conversational or assistant-style search products.
Background in a marketplace or e-commerce company's search, ranking, or recommendations team.

Responsibilities

Build and operate real search infrastructure (Elasticsearch/OpenSearch, Vespa, or vector-search databases like pgvector, Pinecone, or Weaviate) to power ranking and multi-modal search across Nivoda’s marketplace.
Design multi-tenant, configurable ranking and recommendation systems that serve both Nivoda’s own marketplace and many individually branded jeweller storefronts through Feeds, without forking the codebase.
Build and improve Contextual Search and the planned conversational assistant, using prompt design and retrieval-augmented approaches, handling zero-result and tradeoff scenarios gracefully.
Build image-to-attribute and image-to-product-match pipelines using image embeddings for image-upload search.
Build the product around the reality that probabilistic systems can be confidently wrong, designing recovery paths and confirmation steps before high-stakes actions.
Define and run search- and ranking-specific evaluation (offline ranking metrics, interleaving experiments) to determine if a ranking change is actually better.
Evaluate and stress-test foundation model and LLM output directly as part of the engineering process.
Own the full lifecycle of ranking and recommendation models (features, training, evaluation, deployment, and monitoring) using learning-to-rank, embedding-based retrieval, and collaborative filtering techniques.
Design and optimize low-latency, real-time model-serving systems that keep search feeling instant under production load.
Use AI coding agents to build ML infrastructure and pipelines, paired with rigorous evaluation harnesses that catch ranking and retrieval bugs.