Job Title: Agentic AI Developer / AI/ML Engineer
Location: Atlanta, GA
Duration: 12+ Months
Rate: DOE
Experience: 8–10+ years total (5+ years hands-on GenAI/Agentic AI)
Must-Have Skills
· Python (expert level), backend services (Fast API/Django/Flask)
· Agentic frameworks: Google ADK (Agent Development Kit), LangGraph, Lang Chain, MCP (Model Context Protocol), multi-agent orchestration
· RAG architecture: embeddings, chunking, semantic/hybrid retrieval, reranking
· Vector databases: Pinecone, FAISS, Weaviate
· Agent evaluation: task success, tool-call accuracy, groundedness, latency/throughput regression testing
· Prompt engineering & prompt versioning (templates, evaluation gates, rollback)
· Cloud: Google Cloud Platform Vertex AI, BigQuery, GKE (AWS Bedrock/SageMaker or Azure AI a plus)
· Observability: Lang Smith, MLflow, Prometheus, Grafana, ELK
Nice-to-Have
· Agent/Tool Registry design (governance, versioning, access control)
· Agent FinOps (token/cost attribution, usage analytics)
· AutoGen, CrewAI
· OAuth2/OIDC, RBAC/ABAC for agent-tool auth
· ML frameworks: Scikit-learn, TensorFlow, PyTorch, MLOps (Docker, Kubernetes, Terraform, CI/CD)
· Kafka/event-driven pipelines
· Domain exposure: financial services, healthcare, or other regulated enterprise environments
Responsibilities
· Architect agent workflows: planning, reasoning, tool calling, memory/context, guardrails, human-in-the-loop
· Build reusable Python/TypeScript SDKs, REST/GraphQL endpoints for agent tools
· Own RAG pipeline design and tuning for relevance, grounding, latency
· Build agent evaluation harnesses and observability dashboards
· Implement secure, auditable agent-to-system integrations (MCP, JSON-RPC, OAuth/RBAC)
· Partner with architects, security, DevOps, and business stakeholders on production readiness
Never miss an opportunity! Create an alert based on the job you applied for.
