Job Type: Full time

About Multiscale AIMultiscale AI provides AI Agents and Digital Twins for Semiconductor Manufacturing. With offices in Atlanta, San Francisco, and Hyderabad, we help semiconductor manufacturers optimize fabs and achieve measurable results.The RoleWe're building the world's first vertical-AI platform for microelectronics and materials science. Our platform powers autonomous AI agents that design experiments, optimize manufacturing steps, and accelerate scientific discovery. You'll lead the charge in architecting and scaling these agentic systems.What You'll BuildMulti-agent orchestration layers using LangGraph - deterministic, observable, and built to survive real production conditionsMCP server and tool registration APIs that give agents persistent context and shared state across complex workflowsEnterprise security primitives: RBAC for agents, authentication passthrough, user impersonation, and immutable audit trailsNetwork-isolated LLM serving for air-gapped semiconductor customer environmentsRAG pipelines and vector store architectures tuned for materials science and fab domain retrievalCI/CD pipelines and zero-downtime deployment patterns that keep production systems reliableThe API contracts with the core Multiscale AI platform - the foundation everything else depends onSandboxed, per-session compute for agents - isolated containers, orchestration and scheduling of long-running agent workloadsDurable agent state and event streams - checkpointing,



resumable runs, and auditable histories of every agent actionStreaming chat APIs with reconnection, plus monitoring and evaluation of agents in productionWhat We're Looking For3-5 years building production AI/ML systems - shipped and running, not demo-gradeHands-on with LangGraph or equivalent; you have opinions on orchestration frameworks and can defend themYou've thought hard about how agents fail in production and built systems that recover gracefullyExperience with enterprise security patterns: RBAC, auth passthrough, audit logging, or SOC 2 complianceComfortable deploying on GCP (Vertex AI), AWS, or Azure - Docker and Kubernetes are second natureYou understand RAG pipelines end to end - embeddings, retrieval, evaluation, and where they breakNice to HaveAny exposure to semiconductor manufacturing, fab operations, or materials scienceExperience with network-isolated or air-gapped deployment environmentsOpen-source work or side projects in agentic AI - we want to see what you've builtWhy Join UsYou'll architect systems that don't exist yet - real ownership from day oneSmall team, fast decisions, direct access to customers and their hardest problemsWork at the intersection of frontier AI and one of the world's most complex engineering domainsCompetitive compensationLocation: Hyderabad, India. Full-time. Preferred ON SITE. REMOTE can be considered for some positions

📌 Agentic AI Engineer (Gandhinagar)
🏢 Multiscale AI
📍 Gandhinagar