We are looking for AI Engineering Tech Lead to drive the design and delivery of AI agent systems and multi-agent architectures. This is a technical leadership role combining deep hands-on engineering with technical leadership — guiding architectural decisions, mentoring engineers, and maintaining high standards across the codebase.
Requirements
- 5+ years of experience in software engineering with a strong focus on AI/ML systems
- Expert-level Python skills, including async programming and design patterns.
- Demonstrated experience building AI agents and multi-agent systems using LangChain and LangGraph.
- Strong practical knowledge of LLM integration patterns: prompt engineering, function/tool calling, retrieval-augmented generation (RAG), embeddings, and vector search.
- Extensive experience with cloud platforms - AWS and/or Azure - including deployment, scaling, and management of AI workloads.
- Solid general ML foundation: understanding of model training, evaluation, inference pipelines, and the broader ML development lifecycle.
- Strong CI/CD pipeline expertise.
- Hands-on experience with containerization and orchestration in production environments.
- Practical experience with infrastructure-as-code tools for managing cloud resources reliably and repeatably.
- Experience implementing AI observability.
- Proficiency in using AI tools for everyday tasks (Claude Code, Cursor, Advanced prompting, etc)
- Experience designing and building robust APIs (FastAPI, Flask, or similar) and integrating them into larger system architectures.
- Proficiency with SQL and NoSQL databases.
- Ability to lead technical discussions, conduct meaningful code reviews, and mentor team members.
- Upper-Intermediate English or higher.
Would be and advantage:
- High knowledge of core ML frameworks
- Hands-on experience with AWS SageMaker and broader AWS ML ecosystem.
- Solid understanding of the full ML lifecycle.
Responsibilities:
- Lead the technical design and architecture of AI agent platforms and multi-agent workflows built on LangChain and LangGraph.
- Hands-on development of AI agents.
- Integrate LLMs from providers such as OpenAI, Anthropic, and Azure OpenAI into production-grade agent pipelines.
- Build and optimize CI/CD, containerization, and infrastructure-as-code practices for the team.
- Establish and maintain AI observability across agent systems - tracing execution paths, monitoring performance, tracking costs, and surfacing anomalies.
- Mentor and guide engineers through code reviews, architectural discussions, and knowledge sharing sessions.
- Collaborate with product managers, solution architects, and stakeholders to align technical implementation with business objectives.
- Ensure system reliability, scalability, and maintainability through clean architecture, automated testing, and deployment best practices.
- Contribute to defining engineering standards, development workflows, and documentation practices across the team.
- Contribute to technical solutions for AI-oriented proposals during pre-sale cycles