Infosys - Senior Generative AI/Agentic AI Engineer

We are seeking a Senior GenAI / Agentic AI Engineer to lead the design and implementation of production-grade AI solutions for complex enterprise use cases.

The candidate will own AI application architecture, agentic workflows, RAG systems, model integrations, and production engineering.

This role requires a combination of strong hands-on engineering capability and technical ownership.

The candidate will work closely with architects, product teams, data teams, security teams, and engineering stakeholders to build scalable AI solutions.

Key Responsibilities :

AI Solution Design :

- Translate business requirements into scalable GenAI and Agentic AI solutions.

- Design production architectures for LLM-powered applications.

- Select appropriate models, frameworks, retrieval strategies, and deployment approaches.

- Define reusable patterns for enterprise AI application development.

- Evaluate technical trade-offs between different AI architectures and technologies.

Agentic AI Architecture :

- Design multi-agent and multi-step agent workflows for complex enterprise processes.

- Implement tool-calling architectures and AI workflows integrating multiple enterprise systems.

- Design agent memory, context management, orchestration, and state-handling mechanisms.

- Establish controls for agent reliability, failure handling, and deterministic workflow execution.

- Build reusable agent frameworks and components.

RAG & Knowledge Systems :

- Design scalable RAG architectures for enterprise knowledge systems.

- Optimize document ingestion, chunking, embeddings, retrieval, reranking, and context construction.

- Work with vector databases and hybrid search technologies.

- Define strategies for improving retrieval accuracy and response quality.

- Design evaluation frameworks for RAG and LLM-based applications.

LLM Engineering :

- Integrate and evaluate multiple LLM providers and models.

- Design prompt engineering and structured-output strategies.

- Implement model routing, fallback mechanisms, and inference optimization.

- Work with Azure OpenAI and other enterprise model platforms.

- Contribute to model evaluation, fine-tuning, quantization, or optimization initiatives where appropriate.

Production Engineering :

- Design scalable APIs and microservices for AI applications.

- Deploy AI workloads using Docker and Kubernetes.

- Establish CI/CD pipelines for AI application delivery.

- Implement monitoring, logging, tracing, and AI-specific observability.

- Define performance, availability, and scalability requirements.

- Troubleshoot complex production issues and conduct root-cause analysis.

Security & Responsible AI :

- Design security controls for enterprise AI applications.

- Implement guardrails, content controls, access controls, and data protection mechanisms.

- Establish practices for prompt security and protection against common LLM application risks.

- Support Responsible AI, compliance, and governance requirements.

Technical Leadership :

- Lead technical design discussions and architecture reviews.

- Mentor engineers working on GenAI and Agentic AI solutions.

- Conduct code and design reviews.

- Establish development standards and reusable engineering practices.

- Collaborate with product, architecture, security, and data teams.

Required Skills :

- Extensive hands-on GenAI development experience.

- Strong Agentic AI and multi-step workflow experience.

- Python and/or JavaScript/TypeScript.

- LLM application architecture.

- RAG architecture.

- Vector databases and semantic search.

- Azure OpenAI or equivalent enterprise AI platforms.

- LangChain, LlamaIndex, Semantic Kernel, or comparable frameworks.

- API and microservices architecture.

- Docker and Kubernetes.

- CI/CD and cloud deployment.

- AI application observability and evaluation.

Good to Have :

- Multi-agent frameworks.

- Model fine-tuning and quantization.

- Ragas, TruLens, DeepEval, or equivalent evaluation frameworks.

- Event-driven AI systems.

- Real-time inference architectures.

- MLOps / LLMOps.

- Experience with AWS or GCP in addition to Azure.

Candidate Profile :

- Strong combination of hands-on AI engineering and technical leadership.

- Experience taking GenAI solutions from architecture through production.

- Strong understanding of distributed systems and cloud-native engineering.

- Ability to own complex AI initiatives independently.

- Strong stakeholder management and communication skills.

- Ability to mentor engineers and influence technical decisions