LLM & Multi-Agent Solutions Engineer

LLM & Multi-Agent Solutions Engineer

Role Summary:
Build intelligent AI solutions using Large Language Models (LLMs) and multi-agent frameworks for automation, reasoning, and advanced workflows.

Key Responsibilities:

• Develop LLM-powered applications using GPT, Llama, Claude, or similar.
• Build multi-agent systems using LangChain, AutoGen, or custom frameworks.
• Integrate LLMs with external tools, APIs, and enterprise systems.
• Optimize prompts, fine-tune models, and manage vector databases.
• Ensure security, compliance, and performance of AI pipelines.

Requirements:

• Strong experience in generative AI, LLMs, and prompt engineering.
• Familiarity with LangChain, LlamaIndex, AutoGen, or similar frameworks.
• Proficiency in Python, REST APIs, and cloud AI services (Azure OpenAI, AWS Bedrock, etc.).
• Understanding of embeddings, vector databases (FAISS, Pinecone, Chroma), and RAG.
• Experience with MLOps or AI orchestration tools is a plus.

Job Types: Full-time, Permanent

Application Question(s):

• Are you familiar with LangChain, LlamaIndex, AutoGen, or similar frameworks. ?
• What is your expected salary?
• What is your earliest availability to join?

Education:

• Bachelor's (Required)

Experience:

• LLM & Multi-Agent Solutions Engineer: 3 years (Preferred)
• generative AI, LLMs, and prompt engineering: 2 years (Preferred)
• Python, REST APIs, and cloud AI services: 2 years (Preferred)