Senior Engineer - HyperAutomation

Job Title: Senior Engineer - HyperAutomation

GCL: D3

Introduction to role:

Are you ready to unlock agentic AI at enterprise scale to accelerate how life-changing medicines reach patients? This role puts you at the forefront of building autonomous systems that remove friction from complex workflows, sharpen decisions, and create measurable impact across the organization.

You will design and operationalize intelligent agents powered by LLMs and multiagent frameworks, connecting them to real-world systems to drive speed, quality, and trust. Working with Azure OpenAI Services, Azure Cognitive Services, Azure Bot Service, and the breadth of AWS, you will turn promising prototypes into reliable, secure, and compliant products. Can you see yourself transforming experiments into production-grade capabilities that colleagues rely on every day?

Accountabilities:

• Agentic AI Development: Build autonomous agents that observe, decide, and act to streamline high-impact workflows and deliver tangible performance gains.
• LLM Optimization: Finetune and optimize LLMs for agent - based architectures to achieve precise outputs, lower latency, and cost-effective scale.
• Multiagent Orchestration: Engineer coordination strategies, policies, and communication protocols so teams of agents collaborate reliably on complex tasks.
• Enterprise Integration: Connect agents with APIs, databases, and enterprise applications to enable end-to-end automation and actionable insights.
• Memory, Context, and Planning: Implement long-term memory, context retention, and structured planning so agents sustain context across sessions and initiatives.
• Conversational AI: Develop and enhance chatbots and virtual assistants using Azure Cognitive Services, Azure Bot Service, and Azure OpenAI Services that resolve issues and guide decisions.
• Cloud Architecture: Utilize the full suite of AWS services to design, build, and deploy intelligent agents within a scalable, secure, and observable cloud ecosystem.
• Security, Compliance, and Trust: Embed guardrails, auditability, and policy enforcement to meet enterprise standards and earn stakeholder confidence.
• Experimentation to Production: Track advances in autonomous AI, reinforcement learning, and multiagent coordination; translate promising ideas into pilots and production services.
• Impact Measurement: Define success metrics, run A/B tests, and iterate rapidly to deliver quantifiable improvements in accuracy, cycle time, and user satisfaction.
• Stakeholder Partnership: Collaborate with product owners, engineers, and domain experts to align agent behavior with business goals and deliver value fast.
• Scale and Reliability: Advance solutions from proofs-of-concept to highly available services with robust monitoring, alerting, and rollback strategies.

Essential Skills/Experience:

• Design, develop, and deploy AI agents capable of autonomous decision-making and action execution
• Leverage LLMs and multiagent frameworks to create intelligent, interactive AI systems
• Optimize and finetune LLMs for agent - based architectures, ensuring high efficiency and accuracy
• Integrate AI agents with external systems, APIs, databases, and enterprise applications
• Implement techniques for long-term memory, context retention, and planning within AI agents
• Develop and enhance Conversational-AI models, including chatbots and virtual assistants, using Azure Cognitive Services, Azure Bot Service, and Azure OpenAI Services
• Utilizing the full suite of AWS services and tools to design, build, and deploy intelligent agents within a scalable and secure cloud ecosystem
• Ensure scalability, security, and compliance of AI solutions
• Stay up-to-date with the latest advancements in autonomous AI, reinforcement learning, multiagent coordination, and conversational AI technologies

Desirable Skills/Experience:

• Hands-on experience with frameworks such as LangChain, AutoGen, DSPy, or similar agent tooling
• Proficiency in Python and one additional language (such as TypeScript) for service integration and tooling
• Experience with vector databases and RAG patterns (e.g., FAISS, Redis, Pinecone, or Azure Cosmos DB)
• Strong grounding in evaluation methodologies for LLMs and agents, including offline benchmarks and online A/B testing
• Knowledge of MLOps and platform practices (containerization, Kubernetes, CI/CD, model registry, feature stores)
• Familiarity with observability, tracing, and cost governance for AI workloads (OpenTelemetry, logging, metrics)
• Understanding of responsible AI practices, data privacy, and security in regulated environments

When we put unexpected teams in the same room, we unleash bold thinking with the power to inspire life-changing medicines. In-person working gives us the platform we need to connect, work at pace and challenge perceptions. That's why we work, on average, a minimum of three days per week from the office. But that doesn't mean we're not flexible. We balance the expectation of being in the office while respecting individual flexibility. Join us in our unique and ambitious world.

Why AstraZeneca:

Here, your work with autonomous agents and LLMs fuels a bold digital transformation that directly supports the discovery, development, and delivery of medicines. You will collaborate with diverse experts who bring science and technology together, learn through hands-on experimentation and hackathons, and build solutions with investment behind them to scale. We value kindness alongside ambition, encourage open ideas and ownership, and give you the platform to shape modern, data-led capabilities that make a difference for patients and colleagues worldwide.

Call to Action:

If you’re ready to build agentic AI that turns complex challenges into streamlined, measurable outcomes, step into this role and shape the future of medicine with us!

Date Posted

Closing Date

AstraZeneca embraces diversity and equality of opportunity.  We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills.  We believe that the more inclusive we are, the better our work will be.  We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics.  We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorization and employment eligibility verification requirements.