Senior AI Engineer – Agentic Platform
Amtech Software4 days ago
Bengaluru, IndiaSenior
Responsibilities
- Build business logic that operates independently of user interfaces and expose Amtech capabilities as MCP-described tools.
- Build and maintain LLM orchestration and agent execution workflows using LangChain, LangGraph, and MCP.
- Develop and tune RAG pipelines grounded in Amtech data and integrate multiple LLM providers through a common abstraction.
- Build and maintain the Data Agent for governed, read-only access to on-premise customer data with approval gates and queryable audit trails.
- Extend the platform into scheduling, order and customer, documentation and knowledge, forecasting, and KPI intelligence capabilities.
- Create reusable platform components that can be adopted across Amtech product lines and support agents used by Sales, Support, and Customer Success.
- Partner with Forward Deployed Engineers and product pods to validate workflows and inform the platform roadmap.
- Deploy and operate agents and inference endpoints on AWS, including monitoring, evaluations, cost controls, and observability.
- Partner with Data Science, ML Engineering, and MLOps teams on model deployment, monitoring, retraining, feature stores, registries, and model drift practices.
- Set technical direction and review other engineers’ work while serving as a senior technical voice for production practices.
Requirements
- Bachelor’s degree in Computer Science, Software Engineering, Data Science, or a related field.
- 6+ years of software engineering experience, including 2+ years hands-on building production systems with large language models.
- Experience setting technical direction and reviewing other engineers’ work without requiring formal people-management experience.
- Strong Python programming skills.
- Practical experience with prompt engineering, tool or function calling, and agent frameworks such as LangChain or LangGraph.
- Experience integrating at least one major LLM provider API, including OpenAI, Anthropic, Azure OpenAI, or AWS Bedrock.
- Hands-on AWS experience deploying and operating production workloads, including services such as Lambda, ECS/EKS, S3, IAM, and CloudWatch.
- Experience with real-time and batch model inference, including latency, throughput, and cost optimization for LLM or ML workloads.
- Experience building or consuming RAG pipelines and working with vector databases.
- Working knowledge of classical ML engineering and MLOps practices such as feature stores, model registries, and model CI/CD.
- Familiarity with Docker and containerized deployment.
- Working knowledge of Git and CI/CD practices.
- Preferred experience with MCP or similar agent-tool integration standards, governed data-access layers, audit logging, guardrails, and least-privilege access.
- Preferred exposure to Kubernetes, AWS Bedrock, AWS SageMaker, ERP or MES data environments, product or customer-facing engineering, and monitoring tools such as Prometheus, Grafana, or Datadog.
- AWS certification is a plus but is not required.
Benefits
- Access continuous learning, leadership development, and cross-portfolio opportunities through Vista’s global network.
- Work in a collaborative, transparent, people-first environment focused on accountability and integrity.
- Contribute to AI-driven automation and modernization of financial and operational systems.
- Collaborate with peers across Vista’s portfolio and benefit from Vista’s enterprise software ecosystem.
Tech Stack
Categories