Generative AI Engineer - LLM Models

Job Description :

We are looking for a highly skilled and experienced Gen AI Engineer with a strong background in Generative AI technologies and modern cloud ecosystems. The ideal candidate should be well-versed in integrating and validating outputs of Large Language Models (LLMs), have solid programming expertise in Python, and must demonstrate a deep understanding of handling hallucinations and inaccuracies in AI-generated content.

This is a critical role requiring hands-on experience in building, integrating, and testing generative AI applications using models such as OpenAI GPT, PaLM 2, Claude, Dolly, and others. The candidate must also have a solid understanding of cloud environments like AWS and Azure and be able to create scalable and production-ready API-based Responsibilities :

• Design, develop, and implement Gen AI-powered applications and tools using Python and cloud-native services.
• Integrate LLMs (such as OpenAI GPT, PaLM 2, Claude 2, Dolly, Cohere, etc.) using secure and scalable API endpoints.
• Test, validate, and fine-tune LLM outputs to ensure accuracy, context relevancy, and minimal hallucination.
• Collaborate with cross-functional teams to define, estimate, and deliver features aligned with business needs.
• Implement best practices in software development, including unit testing, version control, CI / CD, and performance tuning.
• Create and maintain detailed technical documentation and provide input during architecture and design discussions.
• Work closely with data engineering and product teams to align Gen AI capabilities with broader data analytics and platform goals.
• Leverage Azure and AWS services to design solutions involving storage, logic apps, search indexing, transcription, and real-time chat features.
• Troubleshoot software, APIs, and integration issues, identifying root causes and implementing resolutions Skills :
• Minimum 5+ years of total industry experience with 2+ years dedicated to Generative AI development.
• Expertise in Python programming with experience in building scalable backend or AI-powered services.
• Strong knowledge in Generative AI concepts, prompt engineering, fine-tuning, and hallucination mitigation.
• Proven hands-on experience in integrating at least one popular LLM (OpenAI, PaLM 2, Claude 2, Cohere, Dolly, etc.).
• Familiarity with AWS and Azure cloud platforms, especially serverless components, AI / ML services, and storage solutions.
• Understanding of evaluation metrics for LLMs and techniques for output quality to Have Skills :
• Prior experience in modern data analytics or engineering platforms.
• Proficiency in using Azure services for implementing search, chatbots, transcription, and logic apps.
• Experience with API security best practices and designing scalable APIs for real-time applications.
• Familiarity with containerization (Docker / Kubernetes), MLOps, or similar deployment pipelines.
• Exposure to open-source GenAI frameworks like LangChain, LlamaIndex, or Transformers (Hugging Face).
• Background in NLP, conversational AI, or machine learning lifecycle is a Requirements :
• Strong communication skills and the ability to explain complex AI concepts to non-technical stakeholders.
• Passion for innovation and staying updated with the latest advancements in LLMs and AI / ML technologies.
• Ability to work in a fast-paced agile environment and deliver high-quality software on time.

ref : hirist.tech)