Senior Full Stack AI Engineer

Neutrino Advisory, an Inc 5000 Company; Mumbai; On-site; INR 3,500,000 - 5,000,000; Full time

Job summary

Neutrino Advisory is seeking a Senior Full Stack AI Engineer to join a cloud-native, AI-powered conversational platform on AWS. You’ll work on Python/FastAPI, LLM apps, React, real-time WebSockets, and data platforms.

The role spans backend and frontend engineering, with production-grade LLM capabilities, integration with Bedrock/Claude, and strong AWS services. Candidates should have 8+ years of experience and a focus on scalable architectures.

Qualifications

• 8+ years of software engineering experience.
• Expert Python, FastAPI, async programming, REST API, and WebSocket experience.
• Production experience building LLM/Generative AI applications, including streaming and cost optimization.
• Experience with Amazon Bedrock or equivalent enterprise LLM platforms.
• Experience with AWS Strands, LangGraph, or similar agent frameworks.

Responsibilities

• Build scalable backend services using Python, FastAPI, REST APIs, and WebSockets.
• Develop production LLM capabilities including streaming, prompt orchestration, retries, and safety controls.
• Integrate Bedrock/Claude models and agent frameworks.
• Develop frontend with React and real-time WebSocket interactions.
• Design persistence with PostgreSQL, SQLAlchemy, and Alembic.
• Deploy containerized apps using Docker, ECS Fargate, and Terraform.
• Build CI/CD pipelines with GitHub Actions and automated tests.
• Work with data warehousing and cloud analytics platforms.

Skills

Python

FastAPI

Async programming

REST API

WebSocket

LLM/Generative AI

AWS

Tools

PostgreSQL

SQLAlchemy

Alembic

Docker

GitHub Actions

Terraform

ECS Fargate

Cognito

Job description

Neutrino Advisory is looking for a Senior Full Stack AI Engineer to work on a cloud-native, AI-powered conversational platform built on AWS.

This is a hands-on engineering role spanning Python/FastAPI, LLM applications, React, real-time WebSockets, AWS, and data platforms. We are looking for someone who has built and shipped production applications and can work effectively within an established architecture.

What You'll Work On:

• Build scalable backend services using Python, FastAPI, async programming, REST APIs, and WebSockets.
• Develop production LLM capabilities including streaming responses, prompt orchestration, structured outputs, retries/timeouts, safety controls, and cost optimization.
• Integrate Amazon Bedrock / Claude models and agent frameworks such as AWS Strands or LangGraph.
• Develop responsive frontend applications using React and Vite, including resilient real-time WebSocket interactions.
• Design application persistence using PostgreSQL, SQLAlchemy, and Alembic.
• Implement authentication and authorization using Amazon Cognito, JWT, RBAC, and row-level data controls.
• Deploy containerized applications using Docker, ECS Fargate, ALB, ECR, and Terraform.
• Build and maintain CI/CD pipelines using GitHub Actions with strong automated testing and quality gates.
• Work with data warehouse and analytics architectures, including ingestion, transformation, data modeling, and integration of application/AI data with cloud data platforms.
• Support scalable data pipelines and analytical datasets used for reporting, product analytics, and AI/LLM evaluation.
• Monitor production applications using CloudWatch, Langfuse, and related observability tools.

Must Have:

• 8+ years of software engineering experience with strong hands-on development.
• Expert Python, FastAPI, async programming, REST API, and WebSocket experience.
• Production experience building LLM/Generative AI applications, including streaming, structured output, prompt management, retries, and cost/token optimization.
• Experience with Amazon Bedrock or equivalent enterprise LLM platforms.
• Experience with AWS Strands, LangGraph, or similar agent frameworks.
• Production experience with PostgreSQL, SQLAlchemy, and Alembic.
• Strong AWS experience, particularly ECS Fargate, ALB, VPC, RDS, S3, CloudFront, IAM, KMS, and Secrets Manager.
• Experience implementing Cognito/JWT authentication, RBAC, and secure data access.
• Strong Terraform, Docker, and GitHub Actions experience.
• Experience with data warehousing, ETL/ELT, data modeling, and cloud-based analytical data platforms.
• Strong automated testing discipline using pytest, Playwright, or similar tools.
• Strong communication skills and ability to work with distributed product and engineering teams.

Nice to Have:

• Healthcare, HIPAA/PHI, financial services, or other regulated-system experience.
• Capacitor applications deployed to iOS and Android.
• Three.js / react-three-fiber, 3D avatars, or lip-sync.
• WCAG 2.2 AA accessibility experience.
• LLM trust & safety, guardrails, content moderation, or risk-classification experience.
• Langfuse or similar LLM tracing/evaluation platforms.
• Experience with cloud data warehouse technologies such as Amazon Redshift, Snowflake, Databricks, or equivalent.
• PWA/service workers and mobile CI/CD using fastlane, TestFlight, or Google Play.

Technology Environment:

• AI: Amazon Bedrock, Claude, AWS Strands, Langfuse, Bedrock Guardrails
• Frontend: React, Vite, WebSockets, PWA
• AWS: ECS Fargate, ALB, RDS, S3, CloudFront, Cognito, VPC, WAF, KMS, CloudWatch
• Data: PostgreSQL, ETL/ELT, Data Warehousing, Redshift/Snowflake/Databricks
• DevOps: Terraform, Docker, GitHub Actions, ECR

We are an equal opportunity employer and value diversity at our company.

We do not discriminate on the basis of race, religion, color, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status.

We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process, to perform crucial job functions, and to receive other benefits and privileges of employment.

Please contact us to request accommodation