About the job Senior AI-Ops Engineer
Company Description
Our client, an agency, is searching for a Senior AI-Ops Engineer for their client, a leading AI-driven platform. The agency partners with innovative companies to build scalable AI-native solutions that simplify complex processes. They emphasize ownership, rapid delivery, and pragmatic engineering within a remote-first culture aligned to UK hours.
About the Role
Our client is looking for a Senior AI-Ops Engineer to join their clients elite AI team. In this role, you will own the deployment pipeline of their AI assistant, helping scale it from thousands to hundreds of thousands of users. You will work on advanced multi-agent orchestration, RLHF, and cutting-edge AI infrastructure, shipping code into production from day one and directly shaping the platforms AI strategy.
Key Responsibilities
- Design, build, and maintain production-ready AI deployment pipelines that reliably deliver AI capabilities to real users from day one, ensuring the system scales seamlessly as the platform grows.
- Implement orchestration, monitoring, and fallbacks for multi-agent systems, proactively preventing failures and ensuring the AI assistant performs reliably under heavy load.
- Develop AI application features, including designing intelligent agent behaviors, crafting and optimizing prompts, and deploying innovative capabilities extending beyond traditional infrastructure management.
- Optimize for performance, cost, and reliability, minimizing latency and resource usage while supporting thousands to hundreds of thousands of concurrent users.
- Architect solutions for rapid growth, building scalable and maintainable systems that uphold high quality and stability under evolving requirements.
- Collaborate closely with the AI team, introducing AI-powered development practices, guiding peers, and elevating the technical expertise across the platform.
- Balance hands-on coding (~70%) with infrastructure and deployment tasks (~30%), ensuring both rapid feature delivery and operational excellence.
- Influence technical strategy and long-term architecture, making decisions that shape the future direction of AI capabilities and platform evolution.
Skills & Qualifications
- 3+ years of experience deploying AI systems in production at scale.
- Strong expertise in LLMs, prompt engineering, multi-agent orchestration, and RLHF techniques.
- Proficiency in Python, FastAPI, Pydantic AI, LangGraph, Pipecat, Google Cloud, Anthropic, OpenAI.
- Experience with production deployments using Kubernetes or SageMaker.
- Experience with monitoring frameworks such as LogFire and LangSmith is a plus.
- Frontend integration experience with Next.js and TypeScript is a plus.
- Voice AI deployment experience is a plus.
- Knowledge of Go or Rust is nice to have.
- Multi-modal AI system experience is nice to have.
- Open-source contributions or personal AI projects are nice to have.
- Strong problem-solving, ownership mindset, and ability to ship quickly.
Employment Structure
- Remote in Bangladesh | Full-time
- Salary: BDT 150,000 - 250,000
- Benefits: Flexible time off + Learning budget for conferences & courses + Latest equipment
- Work Week: Monday - Friday, aligned to UK hours
Hiring Process
Technical interview and career journey with Talvette
Technical chat with the clients AI Lead
System design session with the client
Meet the team + culture fit with the client
Receive an offer
- Join their team full-time