Job Title

Job Title: AI DeveloperLocation: RemoteContract Type: Long-Term ContractJob DescriptionWe are seeking a Senior AI Developer with strong expertise in building agentic AI systems, scalable RAG architectures, and production-grade LLM observability. The role involves designing and implementing multi-agent workflows, retrieval pipelines, evaluation frameworks, and safety-aligned AI capabilities across cloud environments (Azure, AWS, GCP). Key Responsibilities • Build and optimize agentic workflows using LangGraph, CrewAI, AutoGen, LlamaIndex Agents, and related frameworks. • Develop scalable RAG pipelines with vector databases (Qdrant, Pinecone, Weaviate, Milvus, FAISS) and hybrid retrieval. • Implement observability using Langfuse and OpenTelemetry for full agent/LLM traceability. • Create LLM evaluation pipelines using DeepEval, Ragas, TruLens, or similar tools. • Design robust memory systems for agents (short-term, long-term, vector memory). • Ensure safety and guardrails for tool execution and policy enforcement. • Deploy AI systems using Kubernetes, automated CI/CD, and cloud-agnostic design patterns. • Integrate AI agents with enterprise systems (Salesforce, ServiceNow, SAP, Workday, Slack, Teams). Required Skills • Agentic Frameworks: LangGraph, CrewAI, AutoGen, LlamaIndex. • RAG Optimization: Vector search, hybrid retrieval, HNSW indexing, metadata filtering. • Observability: Langfuse, OpenTelemetry. • LLM Evaluation: DeepEval, Ragas, TruLens. • Memory Architecture: Short-term, long-term, vector memory; conflict-free state management. • AI Safety: Schema enforcement, reversible tool execution, guardrails. • Cloud & DevOps: Kubernetes, Docker, CI/CD pipelines (GitHub Actions/GitLab/Jenkins). • Enterprise Integration: APIs with Salesforce, ServiceNow, SAP, Workday, Slack, Teams. • Programming: Strong Python engineering skills. • Cloud Platforms: Cloud-agnostic architecture across Azure, AWS, GCP. Ideal Candidate Profile • Proven experience in agentic AI development and RAG architectures. • Hands-on expertise in LLM observability and evaluation frameworks. • Strong background in cloud-native deployments and enterprise integrations. • Ability to design safe, scalable, and production-ready AI systems.