Artificial Intelligence / Machine Learning Engineer - LLM / Prompt Engineering

Key Responsibilities :

• Design, implement, and optimize prompt engineering strategies to elicit high-quality responses from LLMs.
• Fine-tune Google LLMs (PaLM, Gemini) using domain-specific datasets for custom use cases.
• Apply Reinforcement Learning from Human Feedback (RLHF) to improve the performance and decision-making of AI agents.
• Develop and orchestrate intelligent agents using Vertex AI Agent Builder, AutoML, and MCP (Multi-Agent Control Protocol).
• Implement Agent-to-Agent (A2A) architectures and protocols to enable seamless multi-agent collaboration.
• Contribute to the design of scalable and robust agent architectures and evaluation frameworks.
• Collaborate with cross-functional teams including data scientists, product managers, and ML Skills & Qualifications :
• Strong hands-on experience with Python, and ML frameworks like TensorFlow, JAX, and PyTorch.
• Deep understanding of LLM internals, including transformers, LoRA (Low-Rank Adaptation), quantization, and PEFT (Parameter-Efficient Fine-Tuning).
• Experience with Google Cloud AI ecosystem, including Vertex AI, Gemini, and AutoML.
• Practical knowledge of ADK, A2A orchestration, and MCP protocols.
• Experience in designing and optimizing chain-of-thought prompts, zero-shot, few-shot, and instruction tuning strategies.
• Strong problem-solving and algorithmic thinking to Have :
• Experience with conversational AI, knowledge retrieval systems, or multi-turn dialogue agents.
• Familiarity with model compression, distillation, and accelerator optimization.
• Publications or hands-on projects in natural language processing, LLM customization, or RLHF pipelines.

(ref : hirist.tech)