Gen AI Engineer

A highly successful, cutting-edge IoT and Deep-Tech enterprise that has pioneered an innovative, self-powered smart sensor solution designed to inject ambient connectivity and cloud intelligence directly into everyday products and packaging using harvested RF energy.

By seamlessly fusing advanced semiconductor design with a scalable cloud-based SaaS platform, the enterprise enables real-time supply chain tracking, sustainability monitoring, and automated lifecycle management.

The organization maintains an established global footprint, working alongside some of the world's largest and most recognizable international enterprise brands.

The corporate R&D facility is based in a central tech hub (highly accessible, situated directly along the main rail transit network), operating under a hybrid model providing 2 days of remote work per week.

Position Overview-

• Senior Generative AI Software Engineer joining a dedicated, high-caliber GenAI squad tasked with translating massive streams of ambient sensor telemetry into practical, intelligent, and automated user experiences.
• Architecting, deploying, and maintaining production-grade, high-scale Generative AI applications including multi-agent frameworks, agentic workflows, custom copilots, and intelligent Retrieval-Augmented Generation (RAG) architectures.
• Taking full lifecycle ownership of AI application layers: optimizing context design, programmatic function/tool calling, structured prompting, output verification, and system resilience.
• Implementing advanced observability, evaluation, and guardrail architectures to measure system quality, eliminate hallucinations, manage context constraints, and prevent prompt-injection security vulnerabilities.
• Collaborating with platform teams to build developer-facing APIs and custom SDKs that seamlessly surface sensor-driven AI insights.
• Core Domain & Ecosystem- Generative AI & LLM Production Engineering, Agentic Workflows & Frameworks, Advanced RAG Systems, AI Observability & Evaluation Tooling, Python Microservices, IoT Data Pipelines, Security Guardrails, Cloud Architecture (Docker, K8s).

Requirements-

• 5+ years of robust professional experience dedicated to core software engineering, with a proven track record of successfully building, scaling, and shipping production-grade GenAI systems – Mandatory
• Hands-on engineering experience running Generative AI products live in production environments for external customers – Mandatory
• Deep architectural understanding of the unique runtime constraints, failure modes, and lifecycle challenges of modern LLM-driven services – Mandatory
• Strong software engineering fundamentals with production mastery in Python and modern service/infrastructure orchestration frameworks (e.g., FastAPI, Docker, Kubernetes, or equivalent) – Mandatory
• Technical experience working with real-time streaming architectures, sensor data, or complex IoT/ambient-sensing data streams – Strong Advantage
• Prior experience designing developer-focused AI platforms or custom SDKs – Advantage
• Foundational academic or practical background in Natural Language Processing (NLP), Multimodal AI models, or Knowledge Graphs – Advantage
• Hands-on familiarity with autonomous agent libraries and specialized agentic evaluation tooling – Advantage
• Good practical knowledge of core Data Science and statistical fundamentals