Role Summary:

We are seeking a versatile AI Engineer to drive the development of AI agents and ML-driven solutions that create real business impact across language processing, data analysis, and knowledge-centric applications. You will help design and implement AI systems that enhance decision-making, automate complex tasks, and uncover insights while ensuring scalability, reliability, and real-world performance. We’re looking for someone who is adaptable, research-aware, and capable of applying the most effective techniques, whether through prompt engineering, fine-tuning, retrieval-augmented generation, or traditional ML—to solve diverse and evolving challenges.

Key Responsibilities:

• Design and develop AI agents and ML-powered components capable of interacting, reasoning, retrieving knowledge, and completing complex tasks across dynamic environments
• Apply prompt engineering and fine-tuning techniques (e.g., SFT, PEFT, instruction tuning) to tailor LLM behavior to specific objectives, domains, or workflows
• Develop retrieval-based architectures (e.g., RAG pipelines) to enhance contextual awareness and factual accuracy in agent responses
• Design and implement orchestration workflows that enable LLM-based agents to interact with tools, external systems, and other agents to complete complex tasks
• Prepare and manage data pipelines for training, evaluation, and iterative refinement of LLM workflows
• Stay current with advances in LLM research, tools, and best practices, and apply them effectively

Core Expertise:

• Strong foundation in LLMs and machine learning
• Deep understanding of prompt engineering strategies such as zero-shot, few-shot, chain-of-thought, and function calling
• Experience with fine-tuning techniques such as SFT, PEFT, LoRA, and instruction tuning
• Knowledge of retrieval-augmented generation (RAG), long-context modeling, hybrid search and memory integration in agent systems
• Experience handling long-input processing, including tokenization, chunking, context limits, and multi-turn interactions
• Experience with orchestration frameworks to manage tools, reasoning workflows, and task execution including multi-agent collaboration, along with designing feedback loops to monitor agent behavior, improve performance, and reduce drift or hallucinations over time
• Ability to balance prompting, fine-tuning, retrieval, and classical ML approaches based on task requirements and system constraints
• Awareness of alignment, hallucination risks, and behavioral control in LLM-based applications