Role Summary
We are looking for an AI Engineer to design, build, and deploy production-grade Agentic AI and GenAI systems. You will develop scalable AI services, APIs, and secure pipelines integrating LLMs, enterprise systems, and knowledge sources using modern AI engineering practices such as RAG, multi-agent orchestration, evaluation frameworks, and AI guardrails.
Key Responsibilities
- Design and build multi-agent AI systems using frameworks like LangGraph or Semantic Kernel.
- Develop and deploy AI services via APIs using Python, TypeScript, Java, or Go.
- Build RAG pipelines including embeddings, vector databases, and hybrid search.
- Integrate with LLM platforms such as OpenAI, Microsoft, Amazon Web Services, and Google.
- Deploy applications using Docker and Kubernetes.
- Implement testing, monitoring, observability, and AI safety controls.
- Collaborate with cross-functional teams to deliver scalable AI solutions.
Minimum Qualifications
- 6+ years in software engineering building production systems
- Strong coding experience in Python, TypeScript, Java, or Go
- Hands-on experience with Agentic AI / GenAI / RAG
- Experience with vector databases and SQL
- Strong experience in cloud and DevOps (AWS/Azure/GCP, Kubernetes, CI/CD)
- Experience implementing AI evaluation and security best practices
Preferred Qualifications
- Production experience with LangGraph, Semantic Kernel, or Ray
- Advanced retrieval optimization (hybrid search, BM25, re-ranking)
- AI observability and model cost optimization
- Experience in regulated industries (Telco, Finance, Healthcare)
- Multi-tenant and data residency architecture experience
- Experience with TM Forum APIs / BSS-OSS (Telco preferred)
