AI Engineer - Full-time

📋 Description

• • Join Nessolabs as an Artificial Intelligence Engineer and play a pivotal role in building and deploying production-ready Large Language Model (LLM) applications designed to seamlessly integrate into real-world business workflows.
• • This role is centered around practical AI systems, focusing on areas such as retrieval-augmented generation (RAG), intelligent agents, workflow automation, and robust API development. Your primary objective will be to deliver solutions that prioritize reliability, clarity, and measurable business impact, moving beyond mere demonstrations to create tangible value.
• • You will be instrumental in building and shipping LLM-powered features, taking ownership across the entire development lifecycle. This includes everything from initial prototyping and experimentation to full-scale production deployment, encompassing the implementation of sophisticated RAG pipelines, the development of autonomous agents, the integration of tool-calling capabilities, and the automation of complex workflows.
• • A key responsibility will be to implement and optimize retrieval and search pipelines. You will leverage powerful tools like OpenSearch and Elasticsearch, ensuring that indexing strategies and query patterns are meticulously aligned with the actual needs and behaviors of real users, thereby enhancing the accuracy and relevance of AI-driven information retrieval.
• • You will develop and maintain backend services and APIs, primarily using Python. A strong emphasis will be placed on utilizing Pydantic for rigorous data validation, ensuring data integrity and establishing clear, well-defined contracts for all API interactions, which is crucial for system stability and maintainability.
• • The role involves orchestrating asynchronous and scheduled workloads. You will manage and implement solutions for batch jobs, complex data pipelines, and background worker processes using robust frameworks such as Celery and Prefect, ensuring efficient and reliable execution of background tasks.
• • You will be responsible for defining and managing data modeling and persistence strategies specifically for AI workflows. This includes utilizing SQLAlchemy to design efficient database schemas and manage data storage, ensuring that the data underpinning your AI applications is well-structured and readily accessible.
• • Enhancing system observability and reliability will be a critical aspect of your work. You will integrate OpenTelemetry for comprehensive tracing, metrics collection, and logging. This will provide deep insights into system performance, facilitate debugging, and ensure the overall safety and stability of the systems you operate.
• • Collaboration is key in our fully remote, async-first environment. You will work closely with product managers and fellow engineers to align on technical approaches, discuss trade-offs, and ensure continuous delivery of high-quality features. You will actively seek and incorporate feedback based on real-world usage to drive iterative improvements.
• • A proactive approach to identifying and mitigating potential issues is essential. You will be tasked with anticipating edge cases and failure modes, such as LLM hallucinations, retrieval misses, handling long-tail or unexpected inputs, and managing timeouts. Your role will involve developing and implementing pragmatic engineering solutions to address these challenges, ensuring the robustness and resilience of the applications.
• • The core technology stack you will work with includes Python (with Pydantic and SQLAlchemy), the LLM ecosystem (OpenAI SDK, LangChain, LangGraph), search and retrieval technologies (OpenSearch, Elasticsearch), orchestration tools (Celery, Prefect), and observability solutions (OpenTelemetry).
• • This position offers a unique opportunity to work on cutting-edge AI technologies and apply them to solve real business problems, contributing directly to the success and innovation of Nessolabs.