Senior Full Stack Engineer

Role and responsibilities

• As a Senior Full Stack Developer Atlas AI, you will work on building cutting edge Industrial agents and GenAI powered solution for selected strategic customers
• You will work closely with a team of a dedicated M/L engineer and a Technical project manager as well as Strategic business development Atlas AI resource
• Use AI and ML related models, and services as part of the Cognite Data Fusion SaaS platform
• Ensure that integrations are well thought out and robust Important quality criteria for the solution are met (E.g. CI/CD, logging, security)
• Develop technology components in alignment with the  overall technical solution and ensure technical fit within the customer ecosystem and target architecture
• Design integration and data model using Cognite data connectors, Cognite platform components,  SQL, Python/Java and Rest APIs
• Design, develop, and implement generative AI solutions with a strong focus on AI agents, multi-agent systems, and the latest generative AI technologies to drive business innovation and enhance customer experiences
• Collaborate with cross-functional teams to understand business requirements and translate them into technical specifications for generative AI solutions
• In collaboration with Solutions architects, develop scalable AI solutions, including AI agents, that integrate seamlessly with existing systems and leverage cutting-edge technologies
• Develop and deploy AI agents capable of autonomous task execution, environment adaptation, and effective interaction with users and systems, utilizing the latest generative AI frameworks and models

We believe most of these should match your experience

• 5+ years of experience in software engineering, with a focus of 1+ years on Generative AI, machine learning, or intelligent systems.
• Proven experience in developing and deploying multi-agent systems, preferably using frameworks like LangChain. (Mandatory experience) 
• Vector Database Proficiency: Knowledge of vector databases like Pinecone, Milvus, Weaviate, or Faiss, including their architecture and use cases
• Vector Embedding Creation: Experience in generating vector embeddings from textual, visual, or other data using common industry models.
• Skills in creating, managing, and optimizing indexes for efficient similarity search within vector databases, including knowledge of ANN search algorithms.
• Data Ingestion and Querying: Proficiency in ingesting large datasets into vector databases and writing optimized queries for complex similarity searches.
• Scaling and Performance Tuning: Ability to scale vector databases to handle large datasets and optimize search performance through resource management and index tuning.
• Document Retrieval and Prompt Engineering: Skills in designing effective document retrieval strategies and crafting prompts that leverage retrieved documents in the generation process.
• Data Pipeline and Deployment: Expertise in managing data pipelines for RAG systems, from ingestion to retrieval and generation, and deploying RAG systems at scale.
• Experience with knowledge graphs, graph databases, or related technologies.
• RAG Architecture Understanding: In-depth knowledge of Retrieval-Augmented Generation (RAG) systems, integrating retrieval with generative models to produce informed responses.
• Model Integration and Fine-Tuning: Experience in integrating and fine-tuning pre-trained models with retrieval systems in RAG pipelines for enhanced performance
• Proficiency in Python, JavaScript, or other relevant programming languages.
• Deep understanding of multi-agent frameworks, including agent communication, decision-making, and learning strategies.
• Familiarity with cloud platforms (e.g., AWS, Azure) and containerization technologies (e.g., Docker, Kubernetes).
• Experience with API development and integration.
• Knowledge of big data technologies (e.g., Hadoop, Spark) and real-time processing frameworks.
• Data Handling and Storage: Proficiency in reading and writing data in various formats (CSV, JSON, SQL) and using storage tools like SQLite and SQL databases.