Generative AI Cloud Operations Engineer - Evinova

Evinova; Gaithersburg (MD); On-site; USD 134,866 - 202,299; Full time

Benefits offered by this job

Paid vacation and holidays

Comprehensive health benefits

Retirement contributions

Short-term incentive bonus

Job summary

Evinova is looking for a Generative AI Cloud Operations Engineer in Gaithersburg, MD. This role involves designing and developing cloud-native AI systems and managing generative AI workflows to enhance clinical trial processes.

The ideal candidate has a strong background in Python, TypeScript, and AWS services, with at least two years of relevant experience. The position offers a competitive salary and comprehensive benefits including a short-term bonus and health coverage.

Qualifications

• Minimum 2 years of experience deploying genAI workflows in production.
• Strong software engineering skills in Python and/or TypeScript.
• Experience with containerization technologies like Docker and Kubernetes.

Responsibilities

• Drive the design and development of generative AI solutions.
• Manage system performance and predictive analytics.
• Collaborate with cross-functional teams to shepherd projects.

Skills

Generative AI workflows

AWS services

Python programming

TypeScript programming

Collaboration with cross-functional teams

Education

High School Diploma or GED

Tools

Docker

Kubernetes

LangChain

Grafana

Arize Phoenix

Job description

Job Title: Generative AI Cloud Operations Engineer - Evinova Location: Gaithersburg, MD

AstraZeneca, through its subsidiary Evinova, seeks an experienced engineer to lead the design, development, and operation of generative AI solutions for clinical trial design and optimization. The role focuses on building resilient, compliant, and scalable cloud-native AI systems that integrate Large Language Models (LLMs) and rapid deployment pipelines.

Key Responsibilities

• Drive the creation of proactive capabilities and processes that deliver enduring analytic value.
• Design and implement resilient cloud GenAI agent operational capabilities with a focus on learnability, flexibility, extendibility, interoperability, and scalability.
• Manage system performance, cost efficiency, risk mitigation, and predictive analytics across GenAI-based systems.
• Develop and maintain GenAI Ops systems for clinical trial planning and operational optimization.
• Integrate LLM proxies, routers, and RAG pipelines; optimize token usage, latency, and hallucination detection at the platform level.
• Collaborate with AI Engineers, data scientists, and product teams to shepherd projects from research to production-grade agentic capabilities.
• Leverage modern tools and frameworks (LangChain, LangGraph, Google ADK, Langfuse, DSPy, Arize Phoenix, Pinecone, Weaviate, Splunk, Grafana, Prometheus, Xray, Vertex AI, Azure Foundry, OpenAI, Anthropic, etc.) to design, validate, deploy, and monitor AI agents.
• Ensure data-driven design, comprehensive analytics, and evidence-based decision-making for all AI predictions.
• Enhance system scalability, reliability, and performance through effective infrastructure and process management.

Personal Attributes

• Customer-obsessed and passionate about building solutions that solve real-world problems.
• Highly organized, detail-oriented, and able to manage multiple initiatives and deadlines.
• Collaborative and inclusive, fostering a positive team culture that encourages creativity and innovation.
• Proactive in seeking and offering help when needed.

Essential Skills & Experience

• High School Diploma or GED.
• Minimum 2 years deploying and maintaining Generative AI agents or GenAI workflows in production.
• Deep understanding of challenges in deploying generative AI applications and agents.
• Staying current with frontier developments in generative AI, tooling, and techniques.
• Strong grasp of the Data Science Lifecycle and ability to shepherd projects from inception to production within a platform architecture.
• Expertise in LLM evaluation tools such as Arize Phoenix, Langfuse, Braintrust, Freeplay, or similar.
• Expertise in CDK for Python and/or TypeScript.
• Strong software engineering skills in Python and/or TypeScript.
• Expertise in AWS services and containerization technologies (Docker, Kubernetes).
• Experience deploying GenAI agents using frameworks like LangChain, LangGraph, LlamaIndex, Google ADK, or Strands Agents.
• Effective collaboration with engineering, design, product, and science teams.
• Excellent written and verbal communication skills for reporting and documentation.
• Track record of deploying algorithms and machine learning models into production environments.
• Experience working closely with cross‑functional teams, especially data scientists.

Total Rewards

Annual base pay ranges from $134,866.40 to $202,299.60. Hourly and salaried employees receive overtime pay when applicable. In addition to base pay, the role offers a short‑term incentive bonus, eligibility for our equity‑based long‑term incentive program, retirement contributions, paid vacation and holidays, paid leave, and comprehensive health benefits (medical, prescription drug, dental, and vision). The Specifics of benefit plan participation will be provided upon offer.

Equal Employment Opportunity

AstraZeneca is an equal opportunity employer committed to diversity and inclusion, and provides a workplace free from discrimination. We accommodate people with disabilities upon request.