LLM Application Engineer

Tasks

• Build LLM-powered applications
• Build retrieval using vector databases
• Create Orchestration Pipelines
• Debug AI systems end to end
• Design agent workflows
• Develop prompting and context engineering
• Enable structured outputs and tool calling
• Implement evaluation frameworks
• Implement observability tracing experimentation
• Integrate LLMs with tools and APIs
• Optimize model quality latency and cost

Perks/Benefits

• N/A

Skills/Tech-stack

API Integration | Agentic Workflows | Context engineering | Distributed Systems | Evaluation | Experimentation | Generative AI | Information Retrieval | JAX | Language Models | Large Language Models | Observability | OpenAI Compatible | OpenAI Compatible APIs | Orchestration | Prompt engineering | PyTorch | Python | Retrieval-Augmented Generation | Structured Output | Tool-Calling | Tracing | Vector Databases