- 경험
- 3~5세
- 샐러리
- —
- 채용 공고
- 1
- 게시됨
- 18시간 전
- 작업 모드
- 사무실에서
- 교육
- Any Graduate
- 적임
- Any Graduate
- 재개하다
- 신청 시 필수 사항
당신이 일하게 될 곳
직무 설명
About Pragma Edge Software Services
Pragma Edge is a leading IBM Gold Business Partner in North America, recognized as a top I.T. services company in the US. We specialize in delivering innovative IT solutions that facilitate business agility and growth. Our expertise covers advanced B2B integration solutions leveraging IBM Sterling technologies and cloud migration services. As an advanced technology partner to Amazon Web Services, we offer SaaS solutions incorporating big data and blockchain to enhance customer ROI and reduce technological risk.
Role Overview
We seek a Senior AI Engineer with strong expertise in Agentic AI, Large Language Models (LLMs), and cutting-edge NLP. The role involves full lifecycle responsibility for multi-agent system architectures, from initial design to deployment and performance tuning in production environments.
Key Responsibilities
- Develop and deploy agent-based and multi-agent systems using frameworks like CrewAI, LangGraph, AutoGen, and LangChain.
- Create autonomous agents capable of complex reasoning, planning, tool integration, and long-duration task execution.
- Integrate LLMs with diverse tools, APIs, memory storage solutions, vector databases, and Retrieval Augmented Generation (RAG) pipelines.
- Fine-tune foundation models such as Mistral, Gemini Flash, OpenAI, and AWS Bedrock to optimize performance.
- Design advanced prompt engineering techniques and iterative control mechanisms for agent logic.
- Build NLP workflows for text summarization, classification, question answering, and generation.
- Deploy AI services and automated agent workflows to scalable production environments, optimizing for latency, cost, and memory usage.
- Collaborate with DevOps teams on continuous integration, deployment, monitoring, and overall system reliability.
- Establish evaluation methods to measure LLM and agent performance with a focus on robustness and safe AI usage.
- Apply ethical AI principles, governance standards, and AI safety best practices.
- Partner with product, research, data engineering, and software development teams to translate requirements into actionable AI solutions.
- Guide and mentor junior engineers, and actively participate in technical design discussions.
- Document detailed system architectures, decisions, and trade-offs for stakeholder communication.
Qualifications
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or comparable fields.
- 3 to 5 years of practical experience in AI, machine learning, or applied natural language processing.
- Strong programming skills in Python; proficiency with frameworks like PyTorch or TensorFlow.
- Experience with large language models including prompt engineering, fine-tuning, and RAG implementations.
- Scientific know-how in agentic AI development and orchestrating multi-agent systems.
- Proven track record building scalable and distributed AI systems.
- Excellent analytical and communication competencies.
Preferred Skills
- Familiarity with AI frameworks such as WatsonX, LangChain, AutoGen, LangGraph, and CrewAI.
- Experience working with cloud platforms including IBM Cloud, AWS, Azure, or Google Cloud Platform.
- Knowledge of vector databases like FAISS, Pinecone, and Weaviate.
- Engagement in open-source AI projects is a plus.
- Understanding of AI safety, alignment, and ethics.