We are seeking a hands‑on Lead Data Scientist consultant to provide technical direction and drive complex initiatives across search and recommender systems. This role combines deep applied machine learning expertise, systems thinking, rapid prototyping, and cross‑functional influence. The consultant will help shape practical solution approaches, accelerate delivery, and raise technical rigor while remaining accountable for concrete engagement outcomes.
REQUIRED QUALIFICATIONS
- 6+ years of applied machine learning experience, including substantial search and/or recommendation systems experience.
- Strong Python and SQL skills, including experience processing large‑scale data in distributed environments such as Spark.
- Demonstrated experience designing scalable representation‑learning, candidate‑retrieval, ranking, and multi‑stage recommendation architectures.
- Strong foundation in statistics, experimental design, A/B testing, and data analysis.
- Experience building, deploying, or materially contributing to production machine learning systems.
- Track record of leading technical work across multiple teams or disciplines and influencing direction without relying on formal authority.
- Hands‑on experience building or rigorously evaluating LLM‑and agent‑based systems, with clear judgment about appropriate application.
- Understanding of model serving, feature pipelines, monitoring, and practical tradeoffs among model quality, latency, reliability, and scalability.
- Ability to communicate technical decisions, evidence, risks, and recommendations clearly to technical and non‑technical partners.
- Experience working with cloud platforms such as GCP or Azure.
PREFERRED QUALIFICATIONS
- Experience in retail, grocery, e‑commerce, marketplaces, or another high‑scale consumer domain.
- Experience with deep learning architectures for retrieval, ranking, recommendations, or personalization.
- Familiarity with reproducible ML development, model governance, observability, and production incident analysis.
- Experience providing technical mentorship, leading reviews, and establishing reusable patterns across teams.
- Experience evaluating Generative AI, RAG, or agentic workflows in production‑oriented settings.
HOW SUCCESS WILL BE MEASURED
- Delivery of agreed technical outcomes and decision‑ready recommendations within the contract scope.
- Demonstrated improvement in model quality, customer experience measures, business outcomes, or operational readiness, as applicable to the engagement.
- Solutions that meet defined scalability, latency, reliability, maintainability, and monitoring expectations.
- Clear documentation, reproducible work, and effective knowledge transfer to internal teams.
- Strong cross‑functional alignment, timely risk escalation, and well‑supported technical tradeoffs.
Key Responsibilities
WHAT YOU WILL DELIVER
- Technical direction and execution: Lead complex workstreams across search and recommender systems, frame solution options, make clear tradeoffs, and drive work from discovery through production readiness.
- Search and recommendation innovation: Design and validate approaches for representation learning, candidate retrieval, ranking, personalization, and multi‑stage recommendation pipelines tailored to grocery retail.
- Applied AI acceleration: Prototype and rigorously evaluate appropriate Generative AI, RAG, LLM‑evaluation, and agent‑based approaches, with sound judgment about where they add value.
- Evaluation strategy: Define offline and online evaluation methods, experimentation plans, success metrics, and decision criteria that connect model improvements to customer and business outcomes.
- Production partnership: Work with Engineering on real‑time inference, feature access, system integration, monitoring, reliability, latency, and scalability requirements.
- Cross‑functional alignment: Translate business and product needs into clear scientific problem statements, hypotheses, execution plans, risks, and expected outcomes.
- Technical enablement: Lead design and model reviews, document reusable patterns, and provide technical guidance that enables internal team members to sustain and extend delivered solutions.
- Engagement outcomes: Produce agreed deliverables, technical documentation, recommendations, and knowledge transfer within the scope and timeline established for the contract.