Senior Applied AI Engineer

Lead / Senior Applied AI Engineer
Experience: 5–15 Years
Employment Type: Full-Time
Job Description
We are looking for a Lead / Senior Applied AI Engineer with strong hands-on experience in Generative AI, Agentic AI, LLM orchestration, and enterprise AI solutions. The ideal candidate should have experience designing and deploying production-grade AI applications using Python, LangGraph, Agentic RAG, Multi-Agent Systems, and modern LLM technologies.
Key Responsibilities
Design and develop Agentic AI and Multi-Agent Systems using Python and LangGraph.
Build scalable Agentic RAG pipelines and enterprise-grade LLM applications.
Implement LLM orchestration, tool calling, workflow automation, and intelligent agents.
Work with MCP (Model Context Protocol) to integrate AI agents with enterprise tools, data sources, and services.
Develop effective prompt engineering strategies, including structured prompting and reusable prompt frameworks.
Implement Prompt Injection Defense, hallucination mitigation, grounding, validation, and AI safety mechanisms.
Design and implement structured outputs using schemas and validation frameworks.
Work with leading LLM platforms/models including Claude and other enterprise LLMs.
Ensure AI solutions follow AI Safety, security, privacy, and responsible AI principles.
Build CI/CD pipelines and production deployment workflows using Docker, Kubernetes, and DevSecOps practices.
Develop and deploy AI workloads on GCP and integrate with enterprise cloud services.
Collaborate with engineering, security, data, and business teams to deliver enterprise AI solutions.
Ensure AI applications align with applicable regulatory and governance requirements, including EU AI Act and DORA.
Lead technical discussions, architecture decisions, code reviews, and mentoring of AI engineering teams.
Required Technical Skills
Python
LangGraph
Agentic RAG
Multi-Agent Systems
LLM Orchestration
MCP (Model Context Protocol)
Prompt Engineering
Prompt Injection Defense
Hallucination Mitigation
Structured Outputs
Claude / LLMs
Generative AI / Agentic AI
AI Safety & Responsible AI
CI/CD
Docker
Kubernetes
DevSecOps
GCP / Google Cloud
Enterprise AI architecture and deployment
AI Governance & Compliance
Understanding of EU AI Act requirements and AI risk management.
Knowledge of DORA (Digital Operational Resilience Act) and its relevance to technology/AI systems.
Experience implementing AI security, governance, auditability, monitoring, and compliance controls.
Preferred Skills
Experience building production-grade enterprise AI platforms.
Knowledge of LLM evaluation, observability, guardrails, and AI monitoring.
Experience with API development and microservices.
Strong understanding of cloud-native architecture and secure software development.
Experience leading AI engineering teams and working with enterprise stakeholders.

Work arrangement
No