Job
Description
Role Overview: As an AI Development Lead at Newpage Solutions, your mission will be to architect and deliver next-generation Generative AI and Agentic systems. You will play a key role in driving end-to-end innovation, collaborating with cross-functional teams to transform AI research into production-ready solutions. This individual-contributor leadership role requires someone who thrives on ownership, fast execution, and technical excellence, defining standards for quality, scalability, and innovation across all AI initiatives. Key Responsibilities: - Architect, build, and optimize production-grade Generative AI applications using modern frameworks such as LangChain, LlamaIndex, Semantic Kernel, or custom orchestration layers. - Lead the design of Agentic AI frameworks (Agno, AutoGen, CrewAI etc.) to enable intelligent, goal-driven workflows with memory, reasoning, and contextual awareness. - Develop and deploy Retrieval-Augmented Generation (RAG) systems integrating LLMs, vector databases, and real-time data pipelines. - Design robust prompt engineering and refinement frameworks to enhance reasoning quality, adaptability, and user relevance. - Deliver high-performance backend systems using Python (FastAPI, Flask, or similar) aligned with SOLID principles, OOP, and clean architecture. - Own the complete SDLC, including design, implementation, code reviews, testing, CI/CD, observability, and post-deployment monitoring. - Collaborate with MLOps engineers to containerize, scale, and deploy models using Docker, Kubernetes, and modern CI/CD pipelines. - Integrate APIs from OpenAI, Anthropic, Cohere, Mistral, or open-source LLMs (Llama 3, Mixtral, etc.). - Leverage VectorDB such as FAISS, Pinecone, Weaviate, or Chroma for semantic search, RAG, and context retrieval. - Develop custom tools, libraries, and frameworks to improve development velocity and reliability across AI teams. - Partner with Product, Design, and ML teams to translate conceptual AI features into scalable user-facing products. - Provide technical mentorship and guide team members in system design, architecture reviews, and AI best practices. - Lead POCs, internal research experiments, and innovation sprints to explore and validate emerging AI techniques. Qualifications Required: - 7-12 years of total experience in software development, with at least 3 years in AI/ML systems engineering or Generative AI. - Strong Python experience with a solid grasp of OOP, SOLID, and scalable microservice architecture. - Proven track record in developing and deploying GenAI/LLM-based systems in production. - Hands-on experience with LangChain, LlamaIndex, or custom orchestration frameworks. - Deep familiarity with OpenAI, Anthropic, Hugging Face, or open-source LLM APIs. - Advanced understanding of prompt construction, optimization, and evaluation techniques. - End-to-end implementation experience using vector databases and retrieval pipelines. - Understanding of MLOps, model serving, scaling, and monitoring workflows (e.g., BentoML, MLflow, Vertex AI, AWS Sagemaker). - Experience with GitHub Actions, Docker, Kubernetes, and cloud-native deployments. - Strong focus on clean code, system scalability, and performance optimization. - Ability to balance rapid prototyping with long-term maintainability. - Excellent collaboration skills and ability to work independently. - Stay updated on new AI models, frameworks, and best practices. - Bachelors or Masters in Computer Science, Machine Learning, or a related technical discipline.,