GenAI LLM Engineer

Position Title: Gen AI LLM Engineer Position Description: Position Overview We are seeking a solution-oriented engineer who can identify where AI/LLM capabilities can transform business operations and architect practical integrations within enterprise software systems. This is not a traditional ML engineering or data science role focused on model training and deployment infrastructure. Key Responsibilities : AI Solution Strategy & Innovation Identify opportunities where AI/LLM integration can solve business problems and add value Evaluate emerging AI technologies (GPT, Claude, open-source LLMs, agent frameworks) for enterprise applicability Assess and recommend appropriate AI tools and frameworks based on use case requirements and technical constraints Design solution architectures that integrate AI capabilities into existing software products · Build business cases and technical proposals for AI initiatives Stay current with AI/LLM developments and translate them into actionable solutions Hands-On Development & Integration Build production-ready integrations between enterprise applications and AI/LLM services Develop RESTful APIs, microservices, and middleware for AI feature delivery Implement prompt engineering strategies, RAG systems, and AI agent workflows · Create proof-of-concepts to validate AI use cases efficiently Write clean, maintainable, testable code that follows enterprise standards Work with vector databases, embeddings, and semantic search implementations Required Qualifications Experience Profile 5+ years of enterprise software development experience 2+ years actively working with AI/LLM integration in software applications · Proven track record of identifying opportunities and delivering solutions (not just executing requirements) Experience building and consuming RESTful APIs, microservices architectures · Strong understanding of cloud platforms (AWS/GCP/Azure) Hands-on coding experience in Java and Python AI/LLM Knowledge Practical experience integrating LLMs (GPT, Claude, Gemini, or open-source models) into applications Understanding of prompt engineering techniques (zero-shot, few-shot, chain-of-thought) · Familiarity with RAG (Retrieval Augmented Generation) patterns and vector search · Experience with at least one AI framework or SDK (LangChain, LlamaIndex, OpenAI SDK, etc.) · Knowledge of AI agent patterns and agentic workflows Technical Foundation · Strong object-oriented programming and design patterns Experience with enterprise frameworks (Spring Boot, similar) Database experience (SQL, NoSQL, Vector databases) API design and integration patterns · Git, CI/CD, and modern development workflows · Cloud-native development experience Soft Skills · Solution-focused mindset - you see possibilities, not just problems · Strong communication skills to bridge technical and business stakeholders · Comfortable with ambiguity and rapid technology evolution Skills Required: LLM, AI, Google Cloud Platform - Biq Query, Data Flow, Dataproc, Data Fusion, TERRAFORM, Tekton,Cloud SQL, AIRFLOW, POSTGRES, Airflow PySpark, Python, API Experience Required: Specialist Exp: 5+ experience in relevant field Experience Preferred: Hands on experience in building AI solutions to solve business problems across the enterprise Education Required: Bachelor's Degree Education Preferred: Certification Program Additional Safety Training/Licensing/Personal Protection Requirements: Additional Information : Key Responsibilities AI Solution Strategy & Innovation Identify opportunities where AI/LLM integration can solve business problems and add value Evaluate emerging AI technologies (GPT, Claude, open-source LLMs, agent frameworks) for enterprise applicability · Assess and recommend appropriate AI tools and frameworks based on use case requirements and technical constraints Design solution architectures that integrate AI capabilities into existing software products Build business cases and technical proposals for AI initiatives Stay current with AI/LLM developments and translate them into actionable solutions Hands-On Development & Integration Build production-ready integrations between enterprise applications and AI/LLM services Develop RESTful APIs, microservices, and middleware for AI feature delivery · Implement prompt engineering strategies, RAG systems, and AI agent workflows · Create proof-of-concepts to validate AI use cases efficiently · Write clean, maintainable, testable code that follows enterprise standards · Work with vector databases, embeddings, and semantic search implementations