Freelance Machine Learning Engineer Jobs in Oregon

As a Senior Machine Learning Engineer II on the Ads Response Prediction team, you will lead the design and development of core ML models that power Instacart's ads ecosystem. This is a research-leaning role focused on theoretical problem formulation, training methodology, and model quality rather than infrastructure or full-stack engineering. You will tackle fundamental challenges in pCTR modeling such as mitigating selection bias, position bias, and optimizer's curse in training data, improving model calibration across surfaces and domains, and advancing our multi-task learning and sequence modeling capabilities. You will also have the opportunity to shape our next-generation foundation model approach for ads ranking and contribute to cutting-edge retrieval systems like TIGER (Transformer Index for Generative Recommenders), Semantic ID and domain language models.

The Ads Response Prediction team owns all systems, algorithms and ML models to ensure a relevant and engaging Ads experience to customers of all the platforms powered by Instacart. This includes search and exploration retrieval systems, sequential modeling and generative retrieval systems for next interaction recommendations, LLM integrations, relevance models, pCTR models, bidding models and incrementality models. The team optimizes for an efficient marketplace to ensure delightful customer shopping experience, desirable advertiser business outcome and Instacart Ads revenue.

The team has strong ML infrastructure and MLOps support, including Delta/DBT-Spark data pipelines, Ray-based distributed training, and automated model deployment. This means you can focus your energy on advancing modeling science rather than building infrastructure.

• Lead research and development of pCTR and conversion prediction models, with a focus on improving calibration, reducing training data biases (selection bias, position bias, optimizer's curse), and advancing model accuracy across Instacart's ads surfaces.
• Design and implement debiasing techniques such as Mixed Negative Sampling (MNS), Inverse Propensity Weighting (IPW), counterfactual risk minimization, and calibration methods (Platt scaling, isotonic regression) to address systematic prediction biases.
• Contribute to the next-generation Multi-Domain Multi-Task (MDMT) model architecture, incorporating innovations like Mixture-of-Experts (MoE), Transformer layers for sequential user behavior, and LoRA adaptors for scalable domain fine-tuning.
• Drive sequence modeling initiatives including the TIGER generative retrieval system and Semantic ID representation learning, expanding their application across ads surfaces such as Product Details, Search and other placements.
• Collaborate with the broader ML community in the company on the path toward Foundation Models using autoregressive user behavior prediction.
• Formulate and scope ambiguous modeling problems from first principles. Translate business observations (e.g., overcalibration patterns, cold-start underperformance) into well-defined ML research directions with clear evaluation criteria.
• Publish and present findings internally. Contribute to the team's culture of technical rigor through design reviews, paper sharing, and experiment retrospectives.
• Graduate degree (Masters or PhD) in machine learning, statistics, computer science, information retrieval, or a closely related field.

• PhD/Master in machine learning, statistics, computer science, information retrieval, or a closely related quantitative field.
• 6+ years of combined academic and industry experience (including PhD research) applying ML to ranking, recommendation, or prediction problems at scale.
• Deep understanding of CTR/conversion prediction modeling, including familiarity with architectures such as Deep & Wide, DeepFM, DCN, and multi-task learning formulations.
• Strong foundation in causal inference, counterfactual reasoning, and training data bias mitigation. Ability to reason about selection bias, position bias, and propensity-based correction methods.
• Proficiency in Python and deep learning frameworks (PyTorch, Tensorflow, JAX). Fluency in data manipulation tools (SQL, Spark, Pandas).
• Track record of formulating ambiguous problems into well-scoped ML research directions and delivering results through rigorous experimentation.
• Strong written and verbal communication skills. Ability to explain complex modeling decisions to cross-functional stakeholders including product managers and data scientists.

• Experience in ads ranking or auction-based systems (pCTR, bid optimization, ROAS feedback loops, marketplace dynamics).
• Hands-on experience with autoregressive sequence models for user behavior prediction, generative retrieval, or transformer-based ranking architectures.
• Familiarity with learned representations such as Semantic IDs, product embeddings, or other approaches to reducing feature cardinality and cold-start challenges.
• Experience with transfer learning or domain adaptation techniques (e.g., LoRA, adapter-based fine-tuning) applied to recommendation or ranking models.
• Publication record in top-tier venues (KDD, WWW, RecSys, NeurIPS, ICML, SIGIR, or similar).
• Experience mentoring junior engineers or shaping technical direction for a modeling team.
• Familiarity with LLM-driven approaches to recommendation, including prompt-based personalization and AI-assisted model development (AutoML).

#LI-Remote