Staff Machine Learning Engineer

Description

project44 is looking for a Staff Machine Learning Engineer to join our engineering team. You will work in a fast-paced Agile environment designing, building, and implementing best-in-class integrations to accelerate how project44 connects to the world's logistics networks.

About the Role

• Staff ML Engineer to lead the development of next-generation AI/ML systems at Project44, spanning ETA, risk, anomaly detection, and supply chain intelligence. This role sits at the intersection of applied modeling, platform thinking, and production impact, with a mandate to both ship high-value ML capabilities and build reusable Data Science platform primitives that scale across teams.
• In addition, this role will drive the integration of Generative AI, LLMs, and agentic systems into core workflows enabling reasoning-driven diagnostics, automation, and intelligent decision support across the supply chain.
• You will work closely with Data Science, ML Engineering, Data Engineering, Platform, and Product teams to deliver production-grade systems and establish a scalable, repeatable approach to AI development at P44.

What You'll Do

• Drive High-Impact ML Systems Lead end-to-end development of models for ETA, risk, anomaly, and fraud leveraging advanced techniques (embeddings, transformers, hybrid models).
• Build Data Science as a Platform Develop reusable ML infrastructure (features, experimentation, deployment, monitoring) to scale model development and reduce time-to-production.
• Lead GenAI & Agentic Systems Build LLM-powered solutions (RAG, diagnostics, automation, coding agents) and establish guardrails, evaluation, and explainability.
• Translate Business Problems into ML Solutions Convert customer workflows into well-defined ML problems and ensure measurable business impact.
• Drive Experimentation & Evaluation Establish strong offline/online evaluation frameworks tied to business outcomes.
• Collaborate Across Engineering Partner with MLE and DE to build scalable, reliable systems across the ML lifecycle.

What We're Looking For

• Experience 8-10+ years in Data Science / Applied ML with a strong track record of building and deploying production-grade ML systems.
• Core Modeling & Technical Expertise Deep expertise across tree-based models, transformers, probabilistic modeling, and feature engineering, with a strong data-centric mindset.
• Data & Platform Fluency Proficient in SQL and Python, with hands-on experience in modern data platforms (Snowflake/Databricks), pipelines (Spark, Airflow), streaming systems (Kafka), and MLOps tooling.
• GenAI & LLM Capability Experience building RAG systems, working with embeddings and vector databases, and developing LLM-based applications and agentic workflows. Strong understanding of evaluation, guardrails, and safe deployment of GenAI systems.
• Systems & Engineering Mindset Familiarity with distributed systems, APIs, and deployment patterns, with the ability to write clean, production-quality code.
• Analytical Rigor & Diagnostics Strong ability to evaluate model performance, detect edge cases, run root cause analysis, and design robust monitoring and evaluation frameworks.
• Data Quality & Signal Awareness Experience handling messy, real-world data, including drift, bias, missingness, and anomalies, along with tools and techniques to detect and address these issues.
• Modeling Judgment & Trade-offs Ability to identify when to use ML versus heuristics and design pragmatic hybrid solutions. Strong understanding of architectural trade-offs across models and systems.
• Business Impact Orientation Clear understanding of how ML metrics translate to business outcomes, with the ability to balance trade-offs across accuracy, scalability, latency, and customer experience.
• Leadership & Communication Strong problem framing, stakeholder influence, and ability to communicate model behavior and decisions clearly to both technical and non-technical audiences. Proven track record of driving measurable business impact.

Preferred Skills

• Experience in logistics (Ocean, Truckload), supply chain, or high-volume operational systems
• Experience with geospatial data, routing, and tracking systems
• Experience with anomaly detection, fraud modeling, ETA prediction
• Experience building internal platforms or tools for DS teams

What Success Looks Like (6-12 Months)

• Deliver 2 high-impact ML capabilities with measurable customer value
• Establish standardized experimentation, monitoring, and RCA workflows
• Introduce GenAI/agentic capabilities that improve productivity and insight generation
• Reduce time-to-production and increase reuse across DS teams
• Drive measurable improvements in model performance and system reliability

In-office Commitment: This position requires a commitment to contribute to our collaborative culture by working in-office three days weekly.