Senior AI Platform Engineer 

These engineers will operate as hands-on individual contributors, but they need to demonstrate an architect-level mindset when approaching problems.

The role requires the ability to take ideas from exploration → architecture → implementation → deployment → operational monitoring, ensuring the solutions deliver measurable value to both customers and the organization.

Role Responsibilities

The engineers will be responsible for:

• Translating product or business ideas into technical architecture and implementation plans
• Designing and implementing multi-tenant SaaS systems
• Building AI-enabled services and agentic workflows
• Developing scalable backend systems using AWS serverless architecture
• Implementing AI-powered features using RAG and LLM integrations
• Collaborating with product owners and pre-sales teams to refine requirements
• Driving development from prototype → production → monitoring
• Measuring and validating business impact and ROI of implemented solutions
• Leveraging AI-assisted development tools to significantly accelerate delivery

We expect engineers who can deliver the productivity of multiple developers by effectively using modern agentic development tools.

Experience Requirements

• 7–10 years of professional software engineering experience
• Strong hands-on experience building SaaS applications on AWS
• Experience working on production systems at scale

Core AWS Architecture Skills (Mandatory)

Candidates must have hands-on experience with:

• AWS Lambda
• API Gateway
• AWS Step Functions
• Amazon SQS
• Amazon S3
• Aurora PostgreSQL / PostgreSQL
• Event-driven serverless architectures

Experience designing and operating production serverless systems is essential.

Programming Stack (Mandatory)

Candidates must be comfortable working across backend and UI layers.

Backend

• Python (primary backend language)

Frontend

• TypeScript
• React

Candidates should be capable of implementing end-to-end features, including backend APIs and UI components where necessary.

Infrastructure & DevOps

Hands-on experience with:

• Terraform
• AWS SAM

Experience managing infrastructure-as-code deployments for serverless systems is required.

AI Systems Experience

Candidates must have practical experience building AI-enabled applications, including:

• RAG (Retrieval-Augmented Generation) systems
• Experience with LlamaIndex
• Experience with vector search using PostgreSQL (pgvector)
• Implementing semantic search using dense vector embeddings
• Implementing hybrid search combining full-text and semantic search
• Experience designing vector indexing and retrieval pipelines

Stack primarily uses:

• PostgreSQL with pgvector
• Hybrid search (full-text + vector similarity)

Candidates should also have experience integrating with LLM platforms such as:

• AWS Bedrock
• AWS Nova 2 Lite
• AWS Nova 2 Multimodal

Agent Platforms & MCP Architecture

This will come in Great to have part. 

Candidates should have experience building AI agent systems and deploying them in production environments.

Experience with the following is highly desirable:

• Designing agent-based workflows
• Deploying MCP Servers
• Developing MCP Applications
• Implementing AI Agents

Experience deploying these systems on:

• AWS Bedrock AgentCore

Candidates should understand how to design systems where agents interact with data services, APIs, and SaaS platforms in a scalable cloud architecture.

SaaS Architecture Experience

Candidates must have experience with:

• Multi-tenant SaaS architectures
• Serverless SaaS platforms
• Cost optimization strategies for cloud systems
• Observability and monitoring
• Operating and maintaining production SaaS environments

Development Approach

We are specifically looking for engineers who:

• Write production-quality code
• Use AI-assisted development tools effectively

Examples include:

• Codex
• Claude
• Gemini
• Other modern coding agents

The expectation is that these engineers can significantly accelerate development velocity by leveraging these tools effectively.

Location Preference

For collaboration efficiency with our engineering team, we prefer candidates based in the following locations (priority order):

1. Pune – strongly preferred
2. Bangalore
3. Chennai

Candidates located in Pune will be prioritized.

Engagement Details

• Number of positions: 2
• Role title: Senior AI Platform Engineer

Trial Period

The engagement will begin with an initial one-month trial period.

Continuation will depend on performance and delivery during the trial phase.

Interview Process

Round 1 – Architecture & Product Thinking

Duration: 60 minutes

Interviewer: Rohit Ghatol

Focus areas include:

• Architectural thinking
• SaaS platform design
• AI-enabled product development
• Problem-solving approach
• Ownership mindset
• Ability to translate product ideas into working systems

Round 2 – Technical Deep Dive

Duration: 90 minutes

Interviewer: Ashish Gupta (Lead AI Engineer)

Focus areas include:

• AWS architecture
• Python backend engineering
• RAG architecture
• AI agent systems
• Scalability and performance
• Code quality and implementation approach

Candidates should be prepared for in-depth technical discussion in this round.

Candidate Submission

Please share candidate profiles that include:

• Detailed technical experience
• Examples of recent systems the candidate has personally built
• Experience with AWS SaaS architectures
• Experience with AI-enabled systems
• Current location

Candidates should have personally implemented at least one production RAG or AI agent system and be prepared to discuss its architecture in detail