AI Engineer

📋 Description

• • Join Concentrate AI, a stealth, well-funded, and rapidly growing seed-stage company, as an AI Engineer and play a pivotal role in shaping the future of Large Language Model (LLM) integration and management. We are building a unified, OpenAI-compatible API that empowers our customers to access, route, and manage a diverse range of LLMs with unprecedented efficiency. Our mission is to save our clients significant time, drastically cut operational costs, and mitigate risks associated with deploying cutting-edge AI technologies. We are at the forefront of managing high-volume AI traffic and complex log data, providing a robust and scalable platform for businesses to leverage the power of AI.
• • In this fully remote role, you will be instrumental in building, running, and debugging sophisticated LLM applications on top of the Concentrate platform. You will dive deep into production workloads, both customer-facing and internal, pushing the boundaries of our system through rigorous stress testing. Your insights and feedback will be invaluable to our product team, directly influencing the evolution of our platform and services. This is an opportunity to work with state-of-the-art AI technologies, solve complex engineering challenges, and contribute to a product that is redefining how businesses interact with AI.
• • Key Areas of Responsibility:
• • Develop and deploy advanced LLM-powered services, intricate workflows, and innovative applications leveraging the capabilities of the Concentrate platform. This involves understanding the nuances of different LLM architectures and tailoring solutions for specific business needs.
• • Seamlessly integrate our solutions with real-world production applications and diverse operational environments. This requires a deep understanding of system integration, API management, and the challenges of deploying AI in live settings.
• • Design and implement highly reliable and resilient interactions with a variety of LLMs, including industry leaders like OpenAI, Anthropic, and Gemini, as well as open-source models. This encompasses crafting effective prompts, managing tool calling functionalities, implementing robust evaluation frameworks, and establishing comprehensive guardrails to ensure responsible AI deployment.
• • Debug complex failures that may span across different LLM models, API layers, and underlying infrastructure. This demands a systematic approach to problem-solving and a keen ability to pinpoint root causes in distributed systems.
• • Write efficient and scalable code, develop utility scripts, and build small, focused tools to rigorously test system behavior under various conditions, including high load and edge cases.
• • Master the art of reproducing bugs, isolating their root causes with precision, and meticulously documenting findings to facilitate rapid resolution and knowledge sharing within the team.
• • Actively drive improvements to our APIs, refine default configurations, and enhance the overall developer experience for users of the Concentrate platform. Your contributions will directly impact the usability and effectiveness of our product.
• • Collaborate closely with product managers and fellow engineers to translate business requirements and user feedback into technical solutions.
• • Contribute to the development of best practices for LLM integration, prompt engineering, and AI system monitoring.
• • Stay abreast of the latest advancements in the field of AI and LLMs, continuously exploring new techniques and technologies to enhance our platform and offerings.
• • Participate in code reviews, providing constructive feedback and ensuring high standards of code quality and maintainability.
• • Contribute to technical documentation, ensuring clarity and comprehensiveness for both internal and external stakeholders.
• • Engage in incident response, swiftly diagnosing and resolving production issues to maintain service availability and performance.
• • Share learnings and insights from production workloads and stress testing with the broader team, fostering a culture of continuous learning and improvement.
• • Proactively identify potential risks and challenges in LLM deployments and propose mitigation strategies.
• • Contribute to the architectural design and technical roadmap of the Concentrate platform.
• • Champion the adoption of efficient and effective AI development practices within the team and across the organization.
• • Build and maintain strong relationships with internal stakeholders, ensuring alignment on technical priorities and project goals.
• • Take ownership of features and projects from conception through to deployment and ongoing maintenance.
• • Contribute to a positive and collaborative remote work environment, actively participating in team discussions and knowledge sharing sessions.