Generative AI Cloud Operations Engineer - Evinova

AstraZeneca • Gaithersburg, MD

4d • $145,000 - $185,000 • Hybrid

About The Position

Evinova is a health-tech business focused on accelerating better health outcomes by advancing digital transformation across the life sciences sector. Operating at the intersection of healthcare, technology, data, and analytics, we are helping unlock the full potential of digital health, transforming how clinical research is conducted, how care is delivered, and how patients experience healthcare. The Machine Learning and Artificial Intelligence Operations team (ML/AI Ops) is a newly formed platform team that will spearhead the design, creation, and operational excellence of our LLM-based agent deployments, multi-agent orchestration, and conversational AI systems pipelines to catalyze and accelerate science led innovations. This team is responsible and accountable for the design, implementation, deployment, health and performance of all LLM-based applications. We manage ML/AI and broader cloud resources, automating operations through infrastructure-as-code and CI/CD pipelines, and ensure best-in-class operations – striving to push even beyond mere compliance with industry standards such as Good Clinical Practices (GCP) and Good Machine Learning Practice (GMLP). As a Generative AI Cloud Operations Engineer for clinical trial design, planning, and operational optimization on our team, you will lead the development and management of AI operations systems for our trial management and optimization SaaS product. You will collaborate closely with our AI Engineers to transition projects from embryonic research into production-grade AI capabilities, utilizing advanced tools and frameworks to optimize model deployment, governance, and infrastructure performance. This position requires a deep understanding of cloud-native agentic Generative AI deployment methodologies and technologies, AWS infrastructure, and the unique demands of regulated industries, making it a cornerstone of our success in delivering impactful solutions to the pharmaceutical industry.

Requirements

• High school diploma or GED required.
• Minimum of 2 years of hands-on experience deploying, operating, and maintaining Generative AI agents, workflows, or applications in production environments.
• Strong understanding of the challenges associated with production GenAI systems, including reliability, scalability, latency, cost optimization, observability, evaluation, and model performance.
• Hands-on experience deploying agentic AI solutions using frameworks such as LangChain, LangGraph, LlamaIndex, Google ADK, Strands Agents, or similar.
• Strong experience with LLM evaluation and observability, using platforms such as Arize Phoenix, Langfuse, Braintrust, Freeplay, or comparable tools.
• Strong software engineering skills in Python and/or TypeScript, with experience building production-quality systems.
• Deep expertise with AWS cloud services, including deploying and operating cloud-native AI/ML workloads.
• Strong experience with infrastructure as code, including AWS CDK using Python and/or TypeScript.
• Experience with containerization and orchestration technologies, including Docker and Kubernetes.
• Strong understanding of the data science and machine learning lifecycle, with demonstrated experience moving models and AI capabilities from experimentation through production deployment and ongoing operations.
• Experience operationalizing RAG pipelines, LLM applications, or multi-agent systems in production is strongly preferred.
• Demonstrated ability to stay current with rapidly evolving Generative AI models, frameworks, tooling, evaluation techniques, and engineering practices.
• Proven ability to partner effectively with AI/ML engineers, data scientists, software engineers, product teams, and other cross-functional stakeholders.
• Strong written and verbal communication skills, with the ability to clearly document technical solutions, operational processes, and system performance.

Responsibilities

• Drive the creation of proactive capability and process enhancements that ensures enduring value creation and analytic compounding interest.
• Design and implement resilient cloud Genereative AI agent operational capabilities to maximize our system A-bilities (Learnability, Flexibility, Extendibility, Interoperability, Scalability).
• Drive precision and systemic cost efficiency, optimized system performance, and risk mitigation with a data-driven strategy, comprehensive analytics, and predictive capabilities at the tree-and-forest level of our Generative AI-based systems, workloads and processes.
• Develop and manage GenAI Ops systems for clinical trial design, planning and operational optimization.
• Integrate LLM proxies/routers including LiteLLM Proxy/Router or other solutions
• Ensure proper RAG pipeline optimization and scaling
• Integration of token usage, latency, response quality, and hallucination detection tools at a platform level.
• Partner closely with AI Engineers and data scientists to shepherd projects from embryonic research stages into production-grade agentic Generative AI capabilities.
• Leverage and teach modern tools, libraries, frameworks and best practices to design, validate, deploy and monitor Generative AI agents in production (including LangChain, LangGraph, Google ADK, Langfuse, DSPy, Arize Phoenix, Pinecone, Weaviate, Splunk, Grafana, Prometheus, Xray, and more)
• Enhance system scalability, reliability, and performance through effective infrastructure and process management.
• Ensure that any prediction we make is backed by deep exploratory data analysis and evidence, interpretable, explainable, safe, and actionable.
• Leverage Vertex AI, Azure Foundry, OpenAI, Anthropic, and other foundation model platforms to provide reliable and stable access to LLMs

Benefits

• short-term incentive bonus opportunity
• equity-based long-term incentive program
• qualified retirement program [401(k) plan]
• paid vacation and holidays
• paid leaves
• health benefits including medical, prescription drug, dental, and vision coverage

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: High school or GED