Senior AI Engineer – Agentic Platform

About this role

Not quite right? These jobs in Bengaluru match the same skills — apply to a few to improve your chances.

Site Reliability Engineer - Devops, AWS, Python/GO - 4 to 8 years

Cisco

In OfficeBengaluru

Apply

Staff SRE for K8s Platform Team (AWS, Kubernetes, Platform Creation, Helm, Karpenter, Istio)

Okta

In OfficeBengaluru

Apply

Senior Product Engineer - AI Agents (Healthcare)

100ms

In OfficeBengaluru

Apply

Staff Software Engineer - India

Altimate AI

In OfficeBengaluru

Apply

Skills you'll use

What you'll do

• Build business logic that runs independent of any screen — the same capability must work for a person in the UI, an AI agent, or an automated job.
• Expose Amtech capabilities as MCP-described tools so any AI model can call them.
• Build and maintain the LLM orchestration layer that turns model output into safe, governed, tool-using actions.
• Implement and extend agent workflows using frameworks such as LangChain/LangGraph and the Model Context Protocol (MCP).
• Build and tune RAG pipelines for grounding agent responses in Amtech's own data.
• Integrate model-agnostic LLM providers — Claude, OpenAI, Azure OpenAI, AWS Bedrock, and whatever model leads next — via a common provider abstraction, avoiding vendor lock-in.
• Build and maintain the Data Agent — new technology that reads EnCore and other customer data directly for inferencing, with no dependency on legacy point-to-point APIs.
• Ensure every agent action passes governed approval gates before it executes, with a complete, queryable audit trail — customer data stays in the customer's environment while still enabling cloud-LLM reasoning over it.

Who can apply

• Extend the platform into concrete delivered capabilities such as Schedule Intelligence (watching schedules, flagging conflicts and trim-loss, proposing re-sequencing), Order & Customer Intelligence (full-context status across specs, history, and dates), Docs & Knowledge (cited, grounded answers with stale-document detection), and Forecast & KPI Intelligence (plain-language questions over throughput, waste, and OTIF).
• Amtech already runs 10+ active agents company-wide — this role's platform work is what lets patterns from those efforts be reused instead of rebuilt.
• Directly support the Utilization mandate to extend engineering's agent-building cadence to Sales, Support, and Customer Success, so new agents in those functions can be built on the same governed orchestration, RAG, and audit foundation rather than one-off tooling.
• Turn Amtech's first production agent pattern into a reusable platform component that other product pods can adopt without a rebuild.
• Partner with Forward Deployed Engineers embedded in product pods to validate the platform against real workflows and feed field learnings back into the roadmap.
• Deploy agents and inference endpoints on AWS (e.g., Lambda, ECS/EKS, SageMaker) and integrate them into existing APIs and microservices.
• Set up evals, cost controls, and basic observability to catch regressions, drift, or runaway spend before they reach customers.
• Bring enough classical ML engineering and MLOps fluency (feature stores, model registries, CI/CD for models, drift monitoring) to partner effectively with the Data Science, ML Engineering, and MLOps functions, not just the agentic/LLM side of the platform.

Perks & benefits

About Amtech Software

Searching for “Amtech Software jobs” or “jobs at Amtech Software”? You’re in the right place.