AI Engineer

Prometteur Solutions Pvt. Ltd. in Pune, India, is seeking an experienced AI Engineer with a focus on Applied AI and Large Language Models (LLMs) for a full-time, permanent position. This role requires a candidate with 2 years of hands-on experience in developing and deploying production-ready AI solutions for real customers. The ideal candidate will possess a strong understanding of AI/ML fundamentals, robust software engineering skills, and demonstrated experience integrating LLMs and AI services into scalable applications. You will collaborate closely with product and engineering teams to design, develop, and maintain AI-powered features that address genuine business challenges.

Key responsibilities include translating business requirements into practical AI solutions, designing and implementing end-to-end AI workflows, and delivering reliable, user-friendly, and performant customer-facing AI features. You will build backend services and APIs for AI modules, integrate AI services with existing systems, and work with frontend engineers for seamless integration. A significant part of the role involves improving AI output quality through prompt engineering, structured outputs, and implementing guardrails, validations, and fallbacks. Ensuring production readiness by optimizing performance, latency, error handling, monitoring, and cost is crucial. Security and maintainability are paramount, requiring adherence to responsible AI practices, data privacy, and the creation of well-documented, versioned AI components that allow for easy model/provider replacement.

Required skills include strong software engineering fundamentals, experience building production-grade backend services, understanding of async patterns, and scalable service design. Proficiency with LLM APIs (OpenAI, Gemini, Anthropic), frameworks like LangChain or LlamaIndex, and prompt engineering/evaluation methodologies are essential. Experience with unstructured datasets, vector stores (Pinecone, Weaviate, Chroma, FAISS), and basic SQL knowledge is necessary. Backend development experience with secure APIs (REST/GraphQL) and integrating AI modules into microservices or monolith architectures is expected. The must-have experience includes 2 years in applied AI, AI engineering, or ML-driven software development, with a proven track record of delivering AI features to production customers, supported by case studies.

Nice-to-have skills include experience with OCR, speech-to-text/text-to-speech systems, cloud deployment (AWS/GCP/Azure), containerization (Docker), and MLOps best practices. Success in this role will be measured by the active usage of deployed AI features by customers, continuous improvement in AI quality, reliability, and cost efficiency, and the development of scalable, maintainable AI systems aligned with product goals.