Специалист по ИИ и машинному обучению - Франкфурт-на-Майне
Зарплата 2500 € - Colobridge GmbH

What we build

We are building a generational application for support, sales and data analysis functionality. It uses chat, agents and functional calls to external systems.

Requirements:

• 3+ years of professional experience with Python;
• Experience using Generative AI, LLMs, RAG and vector databases in production;
• Ability to write production level code in Python;
• Experience in LLMs agents development for specific multiple tasks;
• Experience of functional calling to connection of external tools and systems;
• Experience with LLM frameworks (i.e. LangChain, LlamaIndex) and prompt engineering techniques;
• Production Experience with LLMs: Proven experience in researching, building, and fine-tuning large language models in production environments.

• Experience with the best practices in software development, including version control, testing, and continuous integration;
• Fundamental knowledge of Data Science;
• Familiarity with the open-source ecosystem, frameworks, and libraries.

Will be plus:

- Experience with Machine Learning Operations

- End-to-end experience in collection data, fine tuned, training, evaluating, testing, and deploying Generative app solutions in production;

- Background in building back-end microservices and data platforms using Python.

Responsibilities

• Write production code that meets high-quality and maintainability standards;

• Selecting the most appropriate Generative AI, Natural Language Processing (NLP), and Machine Learning(ML) model depending on the use case;

• Use your prompt engineering and prompt chaining skills to create new prompts and keep improving on the existing ones;

• LLM engineering, inference, tuning and training language models. Optimization NLP models;

• Deploy services in production environments;

• Develop and implement strategies for prompt engineering, model refinement, and training pipelines to enhance model performance;

• Manage the integration of сompany knowledge into NLP models to improve contextual understanding and output relevance;

• Evaluate and utilize state-of-the-art embedding vectors and encoding methods to ensure optimal model performance;

• Guide the team in the expansion and refinement of taxonomies using large language models, followed by human review for tagging accuracy;

• Drive the adoption of best practices in NLP model development, deployment, and maintenance, staying abreast of the latest industry trends and research;

• Improve our LLMOps infrastructure to have a solid feedback loop with the most appropriate metrics to keep optimizing each use case;

Degree

Computer Science, Engineering, Data science or similar

Tech Stack

Python, SQL, Fastapi, Celery, W&B, Docker, AWS: SQS, S3; APP runner, ECR; CircleCI, Docker Hub, Bitbucket, Localstack, LangGraph, LangChain, LlamaIndex, OpenAI, Mistral, llama 3;