• Job Title: Backend Engineer – AI Products
• Company: Version 1
• Job Type: Full-Time
• Department: AI Products / Engineering
• Experience: 3+ Years
• Location: Mumbai, India
• Work Mode: Hybrid / Remote (Based on company policy)

Role Overview

As a Backend Engineer on our AI Products team, you will design, build, and operate the backend services that power products across Galaxy. You will work with product and engineering teams to implement features end-to-end, from data model to API to production deployment.

Many of these products integrate with Galaxy’s AI Suite, our internal platform for Generative and Agentic AI, built on AWS Bedrock, AgentCore, and SageMaker. Day to day, you’ll mostly be consuming that platform, calling its APIs, wiring LLM and RAG-based features into application logic, and reasoning about prompts and model behavior as part of building a good product, rather than building or owning the platform itself. From time to time, though, you may be asked to contribute directly to the AI stack, so foundational AI knowledge is important.

Key Responsibilities

Backend Engineering
•    Design, build, and maintain backend services and REST APIs that power Galaxy products
•    Design data models and schemas, and work with relational and other data stores as appropriate
•    Apply strong software engineering and distributed systems principles to day-to-day development
•    Write automated tests and maintain CI/CD pipelines for reliable, repeatable deployments
•    Diagnose and resolve production issues related to latency, reliability, and data quality

AI Integration
•    Integrate backend services with Galaxy’s AI Suite (Bedrock, AgentCore, SageMaker-based APIs) built and maintained by the AI Platform team
•    Wire LLM, embedding, and RAG-based capabilities exposed by the AI Suite into application features
•    Apply prompt engineering and function calling at the application level to build reliable AI-powered features
•    Contribute to testing and quality checks for AI-driven features from a product/application perspective

Cross-Stack Contribution
•    Contribute across the stack as needed, such as data pipelines, infrastructure, or frontend touchpoints, depending on team and project needs
•    Partner with full stack engineers, the AI Platform team, and data teams to deliver features end-to-end
•    Balance delivery speed with code quality, maintainability, and operational health

Collaboration & Growth
•    Work closely with product managers and business stakeholders to translate requirements into working software
•    Collaborate with the AI Platform team to stay current on AI Suite capabilities and best practices for consuming them
•    Share knowledge with other engineers on backend and AI-integration best practices
 
Qualifications

Job Title: Backend Engineer – AI Products

Company: Galaxy

Job Type: Full-Time

Department: AI Products / Engineering

Experience: 3+ Years

Education: Bachelor’s degree in Computer Science, Software Engineering, Information Technology, or a related field (or equivalent practical experience)

Location: As per company requirements

Work Mode: Hybrid / Remote (Based on company policy)

• Mandatory Technical Skills
  Programming & Engineering
  
  •    Python
  •    REST API design and development
  •    CI/CD pipelines
  •    Automated testing
  •    Distributed systems fundamentals
  •    Relational database design (e.g. PostgreSQL)
  
  CI/CD & Infrastructure
  •    Kubernetes
  •    Terraform
  •    Docker
  •    Jenkins experience is a plus
  
  AI Familiarity
  •    Working familiarity with Generative AI / LLM concepts: RAG, embeddings, prompt engineering, function calling
  •    Experience integrating applications with LLM or AI platform APIs (e.g. AWS Bedrock or equivalent); deep agentic architecture or model training experience is not required
  •    Comfortable reasoning about prompt behavior and AI output quality from an application/product perspective
  
  Cloud Platforms
  •    Working experience with AWS (or equivalent cloud platform)
  •    Exposure to core AWS services such as Lambda, API Gateway, S3, and CloudWatch is a plus
  
  Data Platforms
  •    Databricks experience is a plus
  
  Production & Operations
  •    Observability (logs, metrics, tracing, alerts)
  •    Monitoring and reliability engineering
  •    Performance tuning and cost optimization
  Security
  •    Experience implementing AuthN/AuthZ (OAuth2/OIDC, SSO), RBAC, and secrets management in production applications
  
  Soft Skills
  •    Strong communication skills; comfortable presenting technical recommendations directly to engineering and business stakeholders
  
  Nice to Haves
  Domain
  •    Experience working within the financial services domain is preferred
  •    Prior experience across Capital Markets, Digital Assets/Crypto, or AI infrastructure is highly desirable
  •    Awareness of the regulatory and compliance landscape relevant to financial services technology delivery
  
  AI & Product
  •    Experience building applications on top of LLM/agentic AI platforms (e.g. AWS Bedrock, SageMaker, or equivalent)
  •    Familiarity with vector databases and embeddings (e.g. pgvector) for AI-powered search/retrieval features
  •    Ability to evaluate AI feature quality from a product/UX lens (accuracy, latency, hallucination handling, graceful degradation), distinct from model-level evaluation owned by the AI Platform team