Match score not available

Python AI/ML Engineer

unlimited holidays - extra holidays - extra parental leave - long remote period allowed

Remote:

Full Remote

Contract:

Full time

Experience:

Mid-level (2-5 years)

Work from:

Argentina

Offer summary

Qualifications:

Minimum of 3 years in AI/ML engineering, Expertise with large language models (Llama, Mistral, OpenAI), Experience with vector databases (Pinecone preferred), Proficient in Python microservices and integration, With hands-on experience in FastAPI and Pydantic.

Key responsabilities:

Develop and deploy AI/ML solutions using LLMs
Utilize AI/ML tools like LangChain and Haystack
Leverage vector databases for optimizing applications
Build Python microservices and maintain APIs
Create optimal semantic search applications

NorthStar Logix Inc Startup http://northstarlogix.com

11 - 50 Employees

See more NorthStar Logix Inc offers

Job description

Role Overview

We are looking for a skilled Python AI/ML Engineer with a minimum of 3 years of experience in developing and deploying machine learning solutions, particularly in conversational AI and semantic search applications. The ideal candidate will have a robust understanding of large language models (LLMs), vector databases, and a range of AI/ML tools and frameworks.

Key Responsibilities

AI/ML Solutions Development: Utilize large language models (LLMs) such as Llama, Mistral, and OpenAI APIs to develop and deploy advanced AI/ML solutions.
Tool and Framework Utilization: Work with AI/ML tools and frameworks including LangChain, Haystack, and LlamaIndex to build robust applications.
Vector Databases: Leverage vector databases like Pinecone (preferred), Milvus, and PGVector to enhance and optimize AI/ML applications.
Microservices Development: Build Python microservices that integrate with OpenAI APIs/LLMs to create end-to-end conversational AI solutions.
API Development: Develop and maintain APIs using Python, FastAPI, and Pydantic.
Transformer Models: Apply transformer models (e.g., GPT) and fine-tune them for specific use cases to improve model performance.
Semantic Search Applications: Create and optimize semantic search applications using likeness scoring (nearest neighbor scoring) techniques to enhance search relevance.
Embedding Creation: Develop complex vector embeddings for vector search. This involves converting data into high-dimensional vectors to facilitate efficient search and retrieval.
Azure Experience: Work with Azure cloud services to deploy and manage AI/ML solutions, including experience with Azure's machine learning tools and services.
Application Building with Agents: If applicable, experience with LangChain, CrewAI, or Autogen for building applications using agents with defined roles.

Qualifications

Minimum of 3 years of experience in AI/ML engineering roles.
Proven expertise with large language models and associated APIs (Llama, Mistral, OpenAI).
Strong experience with vector databases (Pinecone preferred, Milvus, PGVector).
Proficient in building Python microservices and integrating AI/ML solutions.
Hands-on experience with Python, FastAPI, and Pydantic.
Experience with transformer models and fine-tuning techniques.
Demonstrated ability to build and optimize semantic search applications with complex vector embeddings.
Familiarity with Azure cloud services is advantageous.
Experience with LangChain, CrewAI, or Autogen for agent-based applications is a plus.

Preferred Skills

Strong problem-solving and analytical skills.
Excellent communication and teamwork abilities.
Ability to thrive in a fast-paced and dynamic environment.
Continuous learner with a passion for staying updated on the latest advancements in AI/ML technologies.

Why Join Us?