LLM Engineer - Freelancer

About the Role

Day-to-day, you will be working on designing and integrating practical AI features into production systems, focusing on delivery rather than research. This will involve collaborating closely with clients to understand their needs and set realistic expectations. Your ability to communicate technical concepts clearly and advise clients on the best use of AI will be invaluable in this role.

What You Will Do

• Design and integrate LLM-powered features such as chat, summaries, classification, smart search, and document Q&A into existing codebases.
• Build lightweight RAG pipelines using embeddings and vector search to enhance the efficiency of AI systems.
• Work with vector databases like pgvector, Pinecone, and Qdrant to store and manage complex data.
• Implement safe and reliable LLM endpoints using services like OpenAI, Anthropic, or Azure.
• Collaborate directly with clients to shape AI features and reduce manual effort, ensuring that the solutions provided meet their needs and expectations.
• Advise clients on the appropriate use of AI, considering factors such as latency, accuracy, and cost to ensure the best possible outcomes.
• Develop and maintain high-quality, well-documented code that is easy to understand and modify.
• Participate in code reviews to ensure that the solutions developed are of the highest standard and adhere to best practices.
• Stay updated with the latest developments in AI and machine learning to continuously improve the services offered.

What We Are Looking For

• Strong software engineering background with hands-on experience in Python, Node.js, or Ruby.
• Proven ability to integrate LLM APIs into production systems, with experience using services like OpenAI, Anthropic, or similar.
• Ability to design pragmatic AI solutions within existing architectures, considering cost, latency, and reliability constraints.
• Experience building RAG pipelines, embeddings, and vector search, with a good understanding of how these components interact.
• Background in big data or data pipelines, with knowledge of how to manage and process large datasets.
• English B2/C1 level, with excellent communication skills to effectively collaborate with clients and team members.
• Ability to work independently and manage time effectively, prioritizing tasks and meeting deadlines.

Nice to Have

• Experience working with cloud-based services like AWS or Google Cloud.
• Knowledge of containerization using Docker and orchestration with Kubernetes.
• Familiarity with agile development methodologies and version control systems like Git.
• Certification in AI, machine learning, or a related field, demonstrating a commitment to professional development.

Benefits and Perks

• Flexible working hours and the ability to work remotely, allowing for a better work-life balance.
• Opportunity to work on a variety of projects, developing a diverse range of skills and experiences.
• Collaboration with a team of skilled professionals who are passionate about AI and machine learning.
• Access to the latest tools and technologies, ensuring that you have the resources you need to deliver high-quality solutions.
• Professional development opportunities, including training and certification programs to support your career growth.
• Competitive compensation package, reflecting your skills and experience.
• Health and wellness programs, promoting a healthy and balanced lifestyle.

• Develop a strong portfolio showcasing your experience in integrating LLM APIs into production systems, highlighting your ability to design and implement practical AI solutions.
• Stay updated with industry trends, following the latest developments in AI and machine learning to continuously improve your skills and knowledge.
• Practice explaining technical concepts clearly and simply, as this will be essential for advising clients on the best use of AI and communicating your solutions effectively.
• Be prepared to discuss your experience with RAG pipelines, embeddings, and vector search, as well as your approach to integrating these components into existing systems.
• Emphasize your ability to work independently, managing your time effectively and prioritizing tasks to meet deadlines.
• Highlight your understanding of cost, latency, and reliability constraints, demonstrating how you consider these factors when designing and implementing AI solutions.
• Prepare questions for the interviewer, such as what a typical project looks like, how you will collaborate with clients, and what opportunities there are for professional development and growth.