Senior Artificial Intelligence Engineer

Nxtwave Disruptive Technologies (Hiring for a Client); Mumbai, Navi Mumbai; On-site; INR 3,000,000 - 5,500,000; Full time

Job summary

Nxtwave Disruptive Technologies (Hiring for a Client) is seeking a seasoned AI software engineer to lead the design and deployment of multi-agent systems and LLM applications for global clients. You will architect resilient, production-grade AI solutions and drive tool-augmented reasoning workflows across multi-cloud environments.

You will mentor junior engineers, conduct robust code reviews, and help standardize reusable AI microservices, APIs, and observability practices.

Qualifications

• 5-8 years software engineering, including 3+ years shipping production LLM/AI systems.
• Experience building autonomous planning/reflection agents and memory architectures.
• Expert in Python with FastAPI, Go, or Node.js backend frameworks.
• Cloud-native experience with Vertex AI, Azure AI Studio, and production deployments.
• Knowledge of vector databases and infra pipelines (Terraform, BigQuery, Pub/Sub).

Responsibilities

• Lead design and implementation of multi-agent systems using LangGraph, CrewAI, and Google AI SDKs (Vertex AI Agent Builder).
• Architect resilient production-grade LLM apps, advanced RAG pipelines, and autonomous reasoning workflows.
• Build, document, and standardize reusable AI microservices, framework architectures, and secure APIs.
• Deploy, optimize, and manage agent-based systems across multi-cloud environments with Docker and Kubernetes.
• Implement end-to-end observability using LangSmith, Vertex AI Inspector, or Azure Monitor.
• Act as technical stream lead, conduct code reviews, and mentor junior AI engineers.

Skills

Production LLM/AI systems

Python programming

Cloud platforms

Code reviews & mentoring

Multi-cloud deployments

Tools

LangGraph

CrewAI

Vertex AI Agent Builder

Google AI SDKs

Docker

Kubernetes

Job description

Key Responsibilities:

• Lead the design and implementation of multi-agent systems using LangGraph, CrewAI, and Google AI SDKs (Vertex AI Agent Builder).
• Architect resilient production-grade LLM applications, advanced RAG pipelines, and autonomous, tool-augmented reasoning workflows.
• Build, document, and standardize reusable AI microservices, framework architectures, and secure enterprise-grade APIs.
• Deploy, optimize, and manage agent-based systems across multi-cloud environments (GCP, Azure, AWS) using Docker and Kubernetes (GKE/AKS/EKS).
• Implement end-to-end system monitoring, logging, and centralized observability utilizing platforms like LangSmith, Vertex AI Inspector, or Azure Monitor.
• Act as a technical stream lead, conducting robust code reviews, leading architectural discussions, and mentoring junior AI engineering staff.

Required Skills & Qualifications:

• 5-8 years of professional software engineering experience, featuring a minimum of 3 years dedicated strictly to shipping production LLM/AI systems.
• Proven track record building autonomous planning/reflection agents, multi-step reasoning chains, and cross-session memory architectures.
• Advanced, expert-level proficiency in Python alongside backend development frameworks (FastAPI, Go, or Node.js).
• Strong hands-on cloud native experience with Vertex AI, Azure AI Studio, and production container deployment toolsets.
• Solid infrastructure/data engineering foundational knowledge including Vector Databases (Pinecone, Weaviate, Vertex AI Vector Search) and infrastructure pipelines (Terraform, BigQuery, Pub/Sub).

What We Offer:

• Competitive base salary paired with performance incentives and a comprehensive benefits structure.
• High-impact exposure to complex enterprise-level projects with global clients across NA, EMEA, and LATAM regions.
• Continuous professional development and structural upskilling support within a fast-growing, globally distributed AI practice.