AI Technical Lead (Microsoft Copilot)

ASAP-IT SOLUTIONS

Ansprechpartner: Michael Saghroun
munich,  Deutschland
80% RemoteFreiberuflichab sofortDauer 12 Monate100% Auslastung
ITAI AgentsWindows Application Programming InterfaceAzure Machine LearningSolution ArchitectureTechnische LeitungMulti-Agent SystemsGenerative AIArtificial Intelligence Markup Language (AIML)

Beschreibung

The AI Tech Lead serves as the primary technical leader and customer-facing representative for AI and Generative AI initiatives. The role is responsible for translating business requirements into scalable AI solutions, driving architecture decisions, leading development teams, and collaborating directly with customer stakeholders to deliver enterprise-grade LLM, Agentic AI, and Retrieval-Augmented Generation (RAG) solutions.
The individual will provide technical leadership across AI strategy, solution architecture, agent orchestration, retrieval engineering, model governance, observability, evaluation frameworks, and production deployment while ensuring alignment with customer goals, business outcomes, security requirements, and operational excellence.

Key Responsibilities
Customer Engagement & Leadership
  • Act as the primary AI technical lead and trusted advisor for customer stakeholders.
  • Conduct AI discovery workshops, requirement gathering sessions, solution demonstrations, and technical design discussions.
  • Translate business use cases into scalable AI and Agentic AI architectures.
  • Present architecture recommendations, implementation roadmaps, risks, and mitigation strategies to customer leadership teams.
  • Lead technical governance, design reviews, and architecture sign-offs with customer and project stakeholders.
  • Provide thought leadership in Generative AI, Agentic AI, RAG, and enterprise AI adoption strategies.
AI Solution Architecture & Design
  • Define end-to-end AI solution architecture for enterprise-grade Generative AI applications.
  • Design LLM-based applications leveraging advanced prompting, tool use, function calling, and structured outputs.
  • Lead architecture decisions related to model selection, orchestration frameworks, retrieval strategies, and deployment patterns.
  • Establish reusable AI engineering standards, design patterns, and best practices.
Agentic AI & LangGraph Engineering
  • Design and govern LangGraph-based agent workflows.
  • Implement planner, retriever, reader, synthesizer, evaluator, and orchestration patterns.
  • Lead development of multi-agent systems for business process automation and intelligent assistance.
  • Ensure scalability, maintainability, and reusability of agent workflows.
Agno Agent Framework Development
  • Design reusable agent skills using Agno.
  • Define agent composition strategies and reusable AI capabilities across multiple solutions.
  • Drive standardization of agent development practices.
  • Establish reusable AI assets and accelerators.
Retrieval Engineering & RAG Solutions
  • Architect enterprise Retrieval-Augmented Generation solutions.
  • Define document ingestion, chunking, metadata enrichment, and indexing strategies.
  • Lead embedding model selection and optimization.
  • Implement semantic, keyword, and hybrid retrieval approaches.
  • Optimize retrieval pipelines for accuracy, relevance, latency, and scalability.
  • Establish citation grounding and source attribution mechanisms to improve trustworthiness and explainability.
Model Routing & Reliability Engineering
  • Define model selection strategies based on performance, cost, latency, and business criticality.
  • Design intelligent model-routing frameworks across multiple LLM providers.
  • Implement fallback, retry, failover, and degradation mechanisms.
  • Develop resilience strategies for model outages, retrieval failures, and low-confidence responses.
  • Ensure high availability and production readiness of AI solutions.
AI Observability & Evaluation
  • Define enterprise AI observability frameworks.
  • Establish monitoring capabilities for:
  • Response quality
  • Citation accuracy
  • Retrieval effectiveness
  • Confidence scoring
  • Hallucination detection
  • Latency and performance metrics
  • Cost and token consumption
  • Lead development of evaluator agents and automated AI quality assessment frameworks.
Engineering Excellence
  • Lead Python-based development of AI services, APIs, microservices, and integration components.
  • Establish coding standards, design guidelines, testing frameworks, and CI/CD practices.
  • Mentor AI engineers and provide technical leadership across delivery teams.
  • Conduct code reviews and ensure adherence to engineering best practices.
  • Drive automation, quality assurance, and operational excellence initiatives.
Testing & Quality Assurance
  • Define testing strategies for LLM-driven applications.
  • Implement unit, integration, regression, and end-to-end testing frameworks.
  • Establish testing and mocking frameworks for LLMs, embeddings, retrieval systems, and external tools.
  • Ensure AI applications meet reliability, accuracy, security, and compliance requirements.
AI Governance & Security
  • Drive Responsible AI and AI Governance practices.
  • Establish controls for prompt security, access management, data privacy, and compliance.
  • Implement safeguards against hallucinations, prompt injection attacks, and data leakage risks.
  • Ensure adherence to enterprise security and regulatory requirements.

Bewerben