ML Engineer — LLM & RAG for AI CX (Remote)

Intryc (YC S24); San Francisco (CA); On-site; USD 140,000 - 200,000; Full time

Benefits offered by this job

Remote-first policy

Generous stock options

Competitive salary

Pension plan

Private health insurance

Latest tech equipment

Job summary

Intryc, headquartered in San Francisco, is building a performance layer for blended workforces. We design ML systems to evaluate and coach human and AI CX agents, featuring LLM-based retrieval and RAG pipelines.

We value autonomy, data-driven decisions, and rapid experimentation. You will collaborate with a team of ex-Meta/Amazon operators and work on scalable ML solutions across cloud platforms.

Qualifications

• Bachelor's degree in CS/Data Science or related field.
• Foundational knowledge of ML algorithms and model development.
• Understanding of LLMs (OpenAI GPT, Hugging Face) and their applications.
• Familiarity with retrieval systems (Elasticsearch, FAISS, vector databases).
• Proficiency in Python and common ML libraries.
• Strong problem-solving and a willingness to learn new technologies.

Responsibilities

• Collaborate with the team to design, implement, and fine-tune ML models, focusing on LLM-based systems.
• Develop and enhance Retrieval-Augmented Generation (RAG) pipelines for intelligent query processing and knowledge retrieval.
• Experiment with and evaluate pre-trained models and fine-tune them for specific tasks.
• Work with large-scale datasets to ensure efficient indexing, retrieval, and contextual relevance.
• Monitor and improve the performance and scalability of deployed models.
• Stay updated with the latest research in LLMs, RAG, and related fields.
• Assist in debugging, testing, and deploying machine learning pipelines.
• Gather customer feedback and iterate on the models' accuracy based on customer use cases.

Skills

Python

ML fundamentals

LLMs knowledge

Retrieval systems

Problem solving

Education

Bachelor's degree in Computer Science or related field

Tools

Elasticsearch

FAISS

Vector databases

Docker

Kubernetes

Job description

Intryc, headquartered in San Francisco, is building a performance layer for blended workforces. We design ML systems to evaluate and coach human and AI CX agents, featuring LLM-based retrieval and RAG pipelines.

We value autonomy, data-driven decisions, and rapid experimentation. You will collaborate with a team of ex-Meta/Amazon operators and work on scalable ML solutions across cloud platforms.