Machine Learning Engineer - RAG
This role involves building the next-gen Retrieval-Augmented Generation (RAG) by demonstrating sophisticated generative AI services, pipelines, and components to drive the development and delivery of Agentforce. You will work on and ship impactful generative AI platforms, applications, and products used by millions of people every day.

The Role
You will play a critical role in integrating artificial intelligence and generative AI into sophisticated RAG technologies, enterprise Knowledge Graphs, and the latest LLM algorithms and technologies to build the next wave of intelligent agents. You will participate in the end-to-end AI product development lifecycle, designing and developing scalable deep learning and generative AI systems and services. You will collaborate with AI Platform Engineers and Software Engineers to define requirements and develop reusable workflows and ML pipelines.

What You’ll Do:

1. Design and deliver scalable RAG services that can be integrated with numerous applications, support thousands of tenants, and operate at scale in production.
2. Drive system efficiencies through automation, including capacity planning, configuration management, performance tuning, monitoring, and root cause analysis.
3. Participate in periodic on-call rotations and be available to resolve critical issues.
4. Collaborate with Product Managers, Application Architects, Data Scientists, and Deep Learning Researchers to understand customer requirements, design prototypes, and bring innovative technologies to production.
5. Brainstorm with Product Managers, Designers, and Engineers to conceptualize and build new features for our large (and growing!) user base.
6. Produce high-quality results by leading or collaborating heavily to large multi-functional projects that have a significant impact on the business.
7. Help other engineers actively own features or systems and define their long-term health, while also improving the health of surrounding systems.
8. Assist our skilled support team and operations team in triaging and resolving production issues.
9. Mentor other engineers and deeply review code.
10. Improve engineering standards, tooling, and processes.

1. 10+ years of proven experience in ML engineering, building AI systems and/or services.
2. Strong proficiency in NLP and machine learning models.
3. Experience with LLMs and prompt engineering.
4. Proven experience building and applying machine learning models to business applications.
5. Proven track record to innovate and deliver results at scale.
6. Experience with distributed, scalable systems and modern data storage, messaging, and processing frameworks, such as Kafka, Spark, Docker, and Hadoop.
7. Proven understanding of deep learning and machine learning algorithms.
8. Grit, drive, and a strong sense of ownership, coupled with teamwork and leadership skills.
9. Experience with functional or imperative programming languages: PHP, Python, Ruby, Go, C, Scala, or Java.
10. Built with common ML frameworks like PyTorch, TensorFlow, Keras, XGBoost, or Scikit-learn.
11. Experience building batch data processing pipelines with tools like Apache Spark, SQL, Hadoop, EMR, MapReduce, Airflow, Dagster, or Luigi.
12. An analytical and data-driven approach, and know how to measure success with complicated ML/AI products.
13. Led technical architecture discussions and helped drive technical decisions within the team.
14. The ability to write understandable, testable code with an eye towards maintainability.
15. Strong communication skills and you are capable of explaining sophisticated technical concepts to designers, support, and other specialists.
16. Strong computer science fundamentals: data structures, algorithms, programming languages, distributed systems, and information retrieval.
17. A bachelor’s degree in Computer Science, Engineering, Statistics, Mathematics, or a related field, or you have equivalent training, fellowship, or work experience.

1. Expertise in retrieval systems and search algorithms.
2. Familiarity with vector databases and embeddings.
3. Strong background in a wide range of ML approaches, from Artificial Neural Networks to Bayesian methods.
4. Experience with conversational AI.
5. Excellent problem-solving skills; the ability to take on problems the world has yet to solve.
6. Demonstrated track record of cultivating strong working relationships and driving collaboration across multiple technical and business teams.
7. Knowledge of using multiple data types in RAG solutions including structured, unstructured, and graph.