Artificial Intelligence Engineer - LLM

Key Responsibilities :

- Design and optimize advanced prompt engineering strategies tailored to business and domain needs

- Fine-tune LLMs using domain-specific datasets to enhance task performance and contextual accuracy

- Apply Reinforcement Learning with Human Feedback (RLHF) to improve agent decision-making and behavior

- Build and implement intelligent agents leveraging Google Cloud Vertex AI, PaLM, and Gemini

- Collaborate in the design and evaluation of multi-agent architectures and workflows

- Utilize A2A orchestration frameworks and MCP protocols to manage agent communication and interoperability

- Standardize agent interaction using Google's Multi-Agent Communication Protocols (MCP)

- Develop, test, and deploy ML models and agents using Python and frameworks like TensorFlow, JAX, and PyTorch

- Implement model optimization techniques including transformers, LoRA, quantization, and PEFT

- Use AutoML tools for model experimentation and deployment acceleration

- Maintain a strong focus on prompt tuning, chain-of-thought prompting, and reasoning-based output generation

Required Skills :

- Strong expertise in AI/ML model development and LLMs

- Experience with Google Cloud AI tools : Vertex AI, PaLM, Gemini, AutoML

- Proficiency in Python, along with TensorFlow, JAX, and PyTorch

- Hands-on experience in prompt design, LLM fine-tuning, and RLHF

- Experience with A2A orchestration, ADK, and MCP protocols

- Knowledge of transformers, LoRA, quantization, and PEFT techniques

- Ability to design intelligent agents capable of context-aware reasoning

- Familiarity with prompt chaining and chain-of-thought prompting techniques

Nice to Have :

- Prior experience deploying LLM-based applications in production

- Understanding of AI/ML evaluation metrics for agents and LLMs

- Exposure to multi-agent systems in real-world enterprise environments