ML Engineer - Inference

Symbl.ai; United States; Remote; USD 100,000 - 160,000; Full time

Job summary

A leading company in the Conversation AI space is seeking an ML Engineer specializing in Inference to develop and optimize their Nebula large language model. The ideal candidate will have significant experience in machine learning frameworks and play a crucial role in real-time communication solutions. The position encourages innovation and offers a fully remote work environment, providing a competitive salary and comprehensive benefits.

Benefits

100% health coverage for employees

401(k) with 3% matching

18 vacation days and 8 sick days

Generous parental leave

Professional development opportunities

Qualifications

• 5+ years experience in Machine Learning and inference model deployment.
• Strong background in developing production-ready models.
• Hands-on experience with Python and ML frameworks required.

Responsibilities

• Design and implement algorithms for real-time inference in conversation AI.
• Collaborate with teams to integrate ML models into production systems.
• Optimize ML models for performance in resource-constrained environments.

Skills

Machine Learning

Problem-solving

Collaboration

Python

Deep Learning

Inference optimization

Tools

TensorFlow

PyTorch

CUDNN/TensorRT

OpenVino

Job description

Elevating the quality of human life through every conversation

ML Engineer - Inference

Location: United States

Experience: 5 years

About the Team:

At Symbl.ai, our team is dedicated to revolutionizing the field of Conversation AI. We are a collaborative and innovative group, pushing the boundaries of what's possible in AI-driven communication technologies.

About the Role:

As an ML Engineer specializing in Inference at Symbl.ai, you will play a key role in the development and optimization of our Nebula large language model, as well as other Conversation AI projects. You will be responsible for implementing and deploying deep learning models to enable efficient and accurate inference in real-time communication scenarios.

Highlights for ML Engineer - Inference:

Joining Symbl.ai as an ML Engineer focused on Inference offers the opportunity to work on cutting-edge technologies in the Conversation AI space. You will be at the forefront of shaping the future of communication with our innovative product, Nebula, and other exciting projects.

Working as an ML Engineer - Inference, you will:

• Design and implement efficient algorithms and models for real-time inference in Conversation AI applications, with a focus on Nebula.
• Collaborate with cross-functional teams to integrate machine learning models into production systems, ensuring scalability, reliability, and performance.
• Optimize and fine-tune machine learning models for resource-constrained environments, such as edge devices or cloud-based platforms.
• Develop monitoring and evaluation mechanisms to assess the performance and effectiveness of inference models in real-world scenarios.
• Stay updated on the latest advancements in machine learning inference techniques and methodologies, incorporating new approaches into our projects as needed.
• Contribute to the documentation and dissemination of best practices for implementing and deploying machine learning inference solutions.

To excel in this role, you should:

• Possess a strong background in machine learning, with hands-on experience in developing and deploying inference models in production environments.
• Demonstrate proficiency in Python and relevant machine learning frameworks such as TensorFlow or PyTorch.
• Have experience with optimization techniques for machine learning models, including quantization, pruning, and model compression.
• Exhibit strong problem-solving skills and the ability to troubleshoot and debug complex technical issues related to inference.
• Possess excellent communication and collaboration skills, with the ability to work effectively in a remote team environment.
• Show a passion for learning and staying updated on advancements in machine learning inference technologies, with a keen interest in applying these technologies to Conversation AI.
• Be experienced in fundamental libraries for accelerating ML workflows, like CUDNN/TensorRT, ROCm, OpenVino, or OpenPPL. Understanding of one or more ML communication frameworks like NCCL is an advantage.

Please Note: Although we have focused centers in Seattle, WA there are no restrictions on where you can be located for this role - Symbl is fully remote.

Benefits and Perks (US)

• 100% covered health coverage for you, and 90% for your dependents.
• 100% covered Life & AD&D, and short-term disability coverage for you.
• 401(k) with 3% matching.
• Continued education and professional development.
• We are aggressive with our goals and hence speed with predictability are critical when it comes to execution. Symbl’s fixed leave policy of 18 Planned vacation days, 8 sick days, generous maternity, paternity and 16 annual holidays - are carefully curated to deliver on those core company values.
  

About Symbl.ai
We are a venture-funded AI startup building conversational AI since 2018; and the journey of building safe, secure and business-ready AI to solve problems in communication experiences informs a lot of the decisions we make about how we build our technology. Symbl is a developer-first platform whose core mission is to bring understanding and generative AI to every business that relies on understanding human conversations, and give machines the ability to comprehend communications better than humans. We believe this will transform how businesses think about their knowledge and will accelerate the various use cases where unlocking unstructured data for business use cases generates ROI at scale.
We obsess about a great developer experience for all our products, the business-readiness of the AI we build, and pride ourselves in bringing state-of-the-art Large Language Models (LLMs) to multi-modal multi-party conversations.

As an organization, we firmly believe in equal opportunity and do not engage in any form of discrimination based on race, religion, national origin, gender, sexual orientation, age, veteran status, disability, or any other legally protected status. We are committed to maintaining a diverse and inclusive work environment where every individual is respected and valued for their unique contributions.
How to Apply: Email with your cover letter including any relevant links to Github or your recent publications to [e-mail] look forward to getting to know you!