About the role
We are looking for a hands-on AI/ML Engineer with strong experience in generative AI, LLM-based applications, and agentic AI systems. The ideal candidate should have experience building and deploying production-ready AI solutions, particularly involving intelligent agents, RAG architectures, multimodal AI, and scalable AI workflows.
We are particularly interested in candidates who have worked on AI-driven products in the OTT, media, entertainment, sports technology, or subscription-based industries.
Responsibilities:
- Design, develop, and deploy generative AI applications and agentic AI workflows using frameworks such as LangGraph, LangChain, CrewAI, Google ADK, or Semantic Kernel.
- Build intelligent AI agents with tool calling, memory management, multi-step reasoning, and orchestration capabilities.
- Develop LLM-powered applications using RAG pipelines, vector databases, semantic search, and embedding techniques.
- Implement prompt engineering, context optimization, model evaluation, and hallucination mitigation strategies.
- Build scalable backend services and APIs using Python and integrate AI capabilities into microservices-based architectures.
- Work with multimodal AI models to develop content-generation workflows involving text, images, audio, and video.
- Experiment with and integrate models such as OpenAI, Gemini, Claude, Stable Diffusion, and other open-source or commercial models.
- Work on model fine-tuning techniques, LoRA, custom embeddings, and optimization of inference performance.
- Deploy and manage AI applications on AWS, Azure, or GCP using Docker and containerization technologies.
- Optimize AI solutions for production, focusing on latency, scalability, reliability, and inference cost.
Requirements:
- 3-6 years of overall experience in software engineering / AI/ML engineering.
- At least 2 years of hands-on experience in generative AI, LLMs, or AI-powered application development.
- Strong programming experience in Python.
- Hands-on experience with agentic AI frameworks such as LangGraph, LangChain, CrewAI, Google ADK, or Semantic Kernel.
- Strong understanding of LLMs, RAG architectures, vector databases, embeddings, and semantic search.
- Experience building production-grade AI applications and integrating LLMs through APIs.
- Good understanding of prompt engineering, context management, model evaluation, and hallucination control.
- Exposure to multimodal AI applications involving text, image, audio, or video generation.
- Experience with cloud platforms (AWS, Azure, or GCP) and Docker/containerized deployments.
- Understanding of REST APIs, microservices, and scalable backend architecture.
Good to Have:
- Experience with multimodal AI models and content-generation platforms such as Sora, Veo, Runway, Midjourney, Stable Diffusion, or TTS systems.
- Exposure to fine-tuning, LoRA, and custom embedding generation.
- Experience building internal AI platforms, agent SDKs, or reusable AI infrastructure.
- Knowledge of AI safety, data governance, and responsible AI practices.
- Experience optimizing LLM inference latency, token consumption, and operational costs.
- Experience in OTT platforms, media technology, digital entertainment, sports technology, or subscription-based products.
- Someone who has moved beyond basic LLM API integration and has hands-on experience building, deploying, and scaling real-world generative AI applications and agentic workflows in production.