Jr. LLM Engineer(Gen AI) Offline

Job Description:

We're seeking a LLM Engineer who has at least one year of experience with Python as well as has practical experience with Prompt engineering techniques. You will work closely with the team who builds the AI platform as well as other LLM engineers who work on specific customer projects. If you want to quickly grow in the generative AI domain and ready for big challenges, that would be a good place for you. We are looking for someone who has a passion for this field, spending time daily on new research papers, news and new techniques.

Key Responsibilities:

• Developing and refining LLM prompts
• Develop AI pipelines for specific tasks (AI agentic system, chain of prompts, etc.)
• Creatively use different AI techniques to improve pipeline stability and quality (Query expansion, Re-Ranking, Hybrid Search for RAG systems, etc.)
• Testing and evaluating AI outputs
• Fine-tuning LLM models
• Collaborating with team on improving inhouse AI platform
• Keeping up with cutting-edge LLM developments and sharing those with team
• Drive innovation both internally and in customers projects using AI
• Collaborating with team on different internal AI tools

• Collaborating on code and architecture design

   

Qualifications:

• 1+ year of experience with Python
• Experience with Prompt Engineering, and Prompt Engineering techniques
• Experience with AI-related frameworks (LangChain, LlamaIndex, OpenAI, Pinecone, etc.)
• Experience building RAG systems, using RAG techniques to increase performance
• Proactive, self-driven, and comfortable with working in a fast-paced startup environment

Nice-to-have Qualifications:

• Experience working with open source models (e.g. Llama3-3.1)
• Experience with Fine Tuning open source models
• Experience with voice pipeline components (STT, TTS models, ASR and VAD)