Experience:

• 3-6 years of software engineering experience
• at least 1.5 years dedicated to building and deploying LLM-based applications in production

Responsibilities:

• Design, implement, and scale production RAG pipelines
• Build and maintain integrations with vector databases
• Develop systematic LLM evaluation and observability frameworks
• Implement parameter-efficient fine-tuning and instruction-tuning pipelines
• Optimize model serving infrastructure for high-throughput and low-latency inference
• Deploy microservices and orchestrate workflows using containerized environments

Nice to have:

• Experience with open-source model optimization
• custom model evaluations
• contributing to popular generative AI libraries

More skills:

Python, asynchronous programming, FastAPI, robust testing frameworks, LLM orchestration and development frameworks, vector search mechanics, semantic embeddings, database optimization techniques, cloud-native infrastructure, Docker, Kubernetes, managed ML platforms

Other:

• Collaboration with backend engineers, data platform teams, and product managers
• Integration of intelligent capabilities into core software systems
• Utilizing tools like vLLM, TensorRT-LLM, or Triton Inference Server
• Cloud platforms like AWS or GCP