Job Details
Jobgether is hiring a GenAI/LLM Engineer to develop production-ready Generative AI applications for enterprise search, summarization, content generation and other language-based use cases.
The role involves working with commercial and open-source LLMs, designing AI application architecture, improving prompts, integrating embeddings and building scalable AI solutions.
Key Responsibilities:
Build Generative AI applications using commercial and open-source LLMs.
Design and improve prompts, system instructions and few-shot examples.
Work on fine-tuning using techniques such as PEFT and LoRA.
Integrate LLM services with backend and microservices systems.
Build embedding and retrieval-based solutions.
Improve AI performance, response time and inference costs.
Create evaluation methods for testing LLM outputs.
Requirements:
3–7 years of relevant software, AI or ML experience.
Strong Python programming skills.
Experience with LangChain, LlamaIndex or Semantic Kernel.
Understanding of transformers, tokenization and quantization.
Experience with FastAPI or Flask and REST APIs.
Hands-on experience with LLM application architecture and prompt engineering.
Experience deploying AI applications in production.
Bachelor’s degree or equivalent technical education.