The AI Engineer is responsible for designing, optimizing, and automating LLM inference pipelines, ensuring scalability, performance, and cost efficiency while collaborating with AI QA and promp engineers to integrate testing and evaluation processes.

• Own the end-to-end LLM pipeline, ensuring scalability, maintainability, and documentation.
• Design and optimize LLM inference pipelines for production, ensuring scalability and reliability.
• Profile and optimize model performance based on speed, cost, and compute resource utilization.
• Work with cloud-based AI services (AWS, GCP, Azure) to manage compute resources efficiently.
• Monitor and log model performance, identifying areas for optimization.
• Define and implement model evaluation metrics for tracking accuracy, latency, and cost efficiency.
• Automate LLM testing (e.g., hallucination detection, bias monitoring, and robustness checks).
• Collaborate closely with the AI QA Engineer and Prompt Engineer to integrate testing, evaluation, and prompt design into the pipeline.

• Strong Python and ML framework expertise (PyTorch, Hugging Face).
• Deep understanding of LLMs (GPT, Claude, Mistral, etc.) and prompt engineering methodologies.
• Experience with vector databases and retrieval-augmented generation (RAG).
• Experience in profiling and optimizing LLM performance (latency, cost, memory usage).
• Strong knowledge of APIs and cloud AI infrastructure.
• Familiarity with LLM optimization, and deployment strategies is a plus.
• Ability to document pipeline architecture and workflows for cross-team collaboration.

All interested candidates are encouraged to apply through this form.
We highly appreciate all applications, however, only shortlisted candidates will be contacted for the next stages.