Back
Senior, niche LLM/agent specialization reduces pool despite metropolitan location and strong multinational brand.
Core LLM and async Python skills transfer across industries, though enterprise Responsible AI and life-sciences context add domain-specific bias.
Explicit 9+ years, mandatory LLM production experience and specific tech/LLMOps requirements create strict shortlisting filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, build, and deploy autonomous multi-agent workflows with complex state machines, involving agent collaboration and error recovery across multiple domains.
Develop and maintain reusable agent libraries, architectures, testing frameworks, and integrate cloud-based LLM providers within production-grade async FastAPI applications.
Implement observability, evaluation frameworks, enterprise security, and collaborate cross-functionally while mentoring junior engineers in asynchronous Python and LLMOps best practices.
Bachelor's or Master's degree in Computer Science, AI/ML, Engineering, Data Science, or related discipline.
9+ years of software engineering experience, including 2+ years in production LLM-powered application development.
Expert-level asynchronous Python programming and experience with agent orchestration frameworks (LangGraph preferred) and cloud LLM providers (AWS Bedrock, Azure OpenAI, Anthropic Claude, OpenAI GPT-4).
Experience with FastAPI, Docker, Git, CI/CD, cloud platforms (AWS, Azure, or Google Cloud), and implementing enterprise security standards.
Experienced in designing and deploying multi-step autonomous agent systems beyond simple chatbots, including conditional logic and tool-calling.
Skilled in advanced agent design patterns (ReAct, Plan-and-Execute), LLMOps practices, observability tooling, and prompt engineering at scale.
Capable of leading architectural decisions, mentoring teams, and working effectively across globally distributed and diverse technical and business stakeholders.