PepsiCo UK
Website:
pepsico.com
Job details:
Overview
As an AI Principal Engineer specializing in Agentic AI enablement, you will lead the design and delivery of production-grade agent capabilities built on the enterprise AI Backbone across cloud and edge environments – across supply-chain and global functions. You will own end-to-end delivery of key agent modules and integration patterns (MCP/tooling), establish strong evaluation and regression discipline, and drive adoption by partnering with transformation teams, BU, platform engineering, and enterprise application owners. You serve as a technical anchor for the workstream—translating ambiguous business workflows into measurable agent outcomes, proactively identifying risks, proposing options/tradeoffs, and ensuring solutions scale across domains.
Responsibilities
- Architectural Leadership & Strategic Execution (40%)
- Design and Architect transformative agent systems that enable organization-wide scaling, establishing new paradigms in agent architecture that become company standards. (Lead/Execute)
- Pioneer novel agent patterns (tool-use orchestration, multi-agent systems, advanced memory architectures) that dramatically improve performance across the enterprise. (Lead/Execute)
- Transform ambiguous business problems into elegant technical solutions with 10x efficiency gains through innovative approaches to system design. (Lead)
- Optimize critical performance metrics beyond standard benchmarks, creating breakthrough improvements (90th percentile latency reduction, 50%+ token efficiency, near-perfect tool-call reliability). (Execute/Lead)
- Establish architectural governance that propagates excellence across teams and projects. (Lead)
- Advanced Evaluation & Quality Engineering (20%)
- Design scientifically rigorous evaluation frameworks that uncover non-obvious failure modes and edge cases others miss. (Lead/Execute)
- Create organization-level evaluation standards and platforms that scale across multiple teams and projects. (Lead)
- Innovate on automated testing methodologies that dramatically increase code quality while reducing QA overhead. (Execute/Lead)
- Perform sophisticated statistical analysis of system behaviors to predict quality issues before they manifest. (Execute)
- Establish early warning systems for emerging failure patterns. (Execute/Lead)
- Model Architecture & Routing Innovation (15%)
- Architect intelligent routing systems that autonomously optimize for cost, latency, and quality trade-offs. (Lead/Execute)
- Pioneer novel approaches to model selection, fine-tuning, and prompt engineering that set new performance standards. (Lead)
- Create optimization algorithms that continuously improve routing decisions based on real-time feedback loops. (Execute/Lead)
- Develop proprietary techniques for model evaluation that provide competitive advantage. (Execute/Lead)
- Advanced Integration & Ecosystem Development (15%)
- Design scalable integration architectures that become enterprise standards for AI/app connectivity. (Lead)
- Create abstraction layers that dramatically simplify how teams connect AI capabilities to enterprise systems. (Execute/Lead)
- Establish next-generation integration patterns that anticipate future technology directions and enable seamless adoption. (Lead)
- Develop tooling that accelerates integration velocity across the entire organization. (Execute/Lead)
- Organizational Multiplier & Innovation Leadership (10%)
- Serve as technical visionary, elevating the entire AI organization's capabilities through knowledge transfer and mentorship. (Lead)
- Anticipate industry shifts and position the organization to capitalize on emerging technological opportunities. (Lead)
- Create internal communities of practice that accelerate knowledge sharing and collective innovation. (Lead)
- Represent the company's technical excellence externally through publications, speaking engagements, and industry contributions. (Lead)
- Drive cross-functional initiatives that break down silos and create new organizational capabilities. (Lead/Execute)
Qualifications
Minimum Qualifications
- Bachelor’s/Master’s in CS/AI/ML or equivalent experience.
- Expertise in ML (structured and unstructured data) development and engineering
- Proven experience shipping LLM/agent solutions to production with measurable quality and operational practices.
Required Expertise
- 10+ years of Software Development Experience.
- Advanced Software Engineering: Python (and Java) mastery with distributed systems expertise; performance optimization (profiling, parallelization); architecture patterns (e.g., FastAPI, asyncio, Pydantic)
- LLM & Agent Systems: Multi-agent orchestration (LangChain, LangGraph, CrewAI); advanced prompt engineering; custom agent memory architectures; model optimization techniques
- Evaluation Framework Development: Statistical evaluation design (confidence intervals, power analysis); benchmark creation; instrumentation frameworks (e.g., MLflow, Arise); regression testing systems
- ML Operations: Production deployment pipelines (Docker, Kubernetes, Ray); model registry management; scaled inference optimization; GPU utilization optimization
- Enterprise Integration: Enterprise connector development; scalable API architectures; data pipeline engineering (Kafka, gRPC, Redis); authorization protocol implementation
- Observability Engineering: Telemetry system design (Prometheus, OpenTelemetry); automated anomaly detection; distributed tracing; performance dashboarding (Grafana)
- System Architecture: Microservice design patterns; high-throughput event processing; fault-tolerance implementation; horizontal scaling architectures
- Technical Leadership: Architecture governance systems; engineering standards development; build-vs-buy evaluation frameworks; technical roadmap creation
Good-to-have Skills
- Full-stack dev experience on modern stack
- Modelling User Interactions with AI Systems; Modeling multi-agent behaviour loops with tools like Temporal
- Agentic memory Patterns and usage with tools like MEM0 and Temporal
- Experience with Agentic RAG; Domain level Semantic Layer Designs with Graph and Vector DBs
Differentiating Competencies Required
- Identify any differentiating behaviors, leadership skills or soft skills required for success in the role.
- Ownership: drives outcomes end-to-end for a workstream area (not just tasks)
- Collaboration & customer focus: influences stakeholders to deliver workflow value and adoption
- Communication & adaptability: executive-ready clarity on progress, risks, and evaluation evidence
- Proactiveness & initiative anticipates constraints, proposes options/tradeoffs early
- Strategic thinking: contributes to roadmap sequencing and reusable patterns across domains
Key Differentials :
- Demonstrates proven history of creating solutions with order-of-magnitude improvements over standard approaches
- Possesses rare combination of deep technical expertise and strategic business understanding
- Creates solutions that scale beyond their direct involvement (leveraged impact)
- Consistently elevates the performance of teams and individuals around them
- Identifies and solves problems others haven't recognized yet
- Maintains extraordinary productivity while ensuring knowledge transfer
- Balances technical perfectionism with pragmatic business value
- Communicates complex technical concepts effectively to both technical and non-technical stakeholders
Click on Apply to know more.