Create and orchestrate LLM-powered user experiences for end users

Develop Python API server code to handle requests from single or multiple front-end clients

Build innovative LLM client code optimized for high-traffic production use

Integrate and utilize the latest LLM models and services

Develop intuitive prompting frameworks to support prompt engineers and subject matter experts

Write SQL queries and contribute to database schema design

Participate in high-level architecture discussions within the CoCounsel AI Skills team and collaborate with other teams

Bachelor’s or Master’s degree in Computer Science or a related field

At least 3 years of production-level experience in software engineering, preferably on an engineering or product team

Advanced proficiency in Python

Strong experience with HTTP API development, including FastAPI and REST API

Proficient in SQL for database management and queries

Experience with Docker for containerization

Familiarity with stages of the machine learning lifecycle, such as data labeling, curation, cleaning, model training, evaluation, and serving

Excellent analytical and problem-solving skills

Ability to work independently and as part of a collaborative team

Demonstrated strong software engineering judgment

Fluent English communication skills, both written and spoken, at B2+ level or higher

Experience with monitoring and logging tools such as Kibana

DevOps experience with Kubernetes

Knowledge of Large Language Models (LLM)

Experience using large language models through code, including services from OpenAI, Anthropic, Cohere, or open-source models like Llama and Mistral

Familiarity with LLM prompting techniques