Senior Backend Engineer
Third AI Automation Inc
- Pay
- ₹20–35 lakh a year
- Experience
- 4–6 years
- Location
- Gurugram · On-site
- Job type
- Full time permanent
- Python
- Nodejs
- microservices
- distributed systems
- AWS
- GCP
- Azure
- monitoring
About the role
Design and build scalable backend services for an enterprise AI platform. Ensure system reliability, observability, and performance across cloud and on-prem deployments. Own end-to-end delivery of backend features with high architectural influence.
What you’ll do
- Design and develop scalable backend services using Python/Nodejs (Python Preferred)
- Build and maintain microservice-based architectures
- Design distributed systems with clear service boundaries
- Own API contracts, data models, and inter-service communication
- Implement async processing, background jobs, and event-driven workflows
- Design systems for horizontal scaling, high availability, and fault tolerance
- Identify and resolve performance bottlenecks across services and data stores
What we’re looking for
Must have
- Python
- Nodejs
- microservices
- distributed systems
- AWS
- GCP
Nice to have
- Neo4j
- graph databases
- LLMs
- RAG pipelines
- embeddings
- GenAI
What makes this role challenging
- Building and operating distributed systems with high reliability and observability
- Integrating LLM-driven pipelines with enterprise systems
- Supporting both cloud and on-prem deployments with varying constraints
- High ownership and ambiguity in a startup environment
What success looks like
- First 30 days
- Ramped on the codebase, shipped small backend changes, and contributed to observability setup.
- By 90 days
- Owning a microservice end-to-end, handling production incidents, and improving system reliability.
- First year
- Leading architectural decisions for a key backend domain, mentoring peers, and driving performance improvements.
Tech stack
- Python
- R
- C++
- Java
- LLMs
- RAG architecture
About Third AI Automation Inc
ThirdAI Automation is an industrial AI company specializing in developing an agentic framework for root cause analysis (RCA) and knowledge mining. Its platform connects to equipment logs, sensor data, and operational records to automatically identify causes of failures and quality issues in complex industrial environments, primarily targeting semiconductor fabs and other manufacturing facilities.
Industrial AI / Semiconductor Manufacturing · Seed · 15-19 employees
Role Summary We are building a B2B enterprise AI platform focused on RAG-based intelligence, Root Cause Analysis (RCA), Knowledge Graphs, and deep enterprise integrations. We are looking for a strong backend engineer with experience in microservices, distributed systems, and scalable architectures, who can design, build, observe, and operate backend services end-to-end. You will work closely with LLM-driven pipelines and ensure systems remain reliable, observable, and performant across cloud and on-prem deployments. This is a hands-on startup role with high ownership and architectural influence. Key Responsibilities Backend & System Design
- Design and develop scalable backend services using Python/Nodejs (Python Preferred)
- Build and maintain microservice-based architectures
- Design distributed systems with clear service boundaries
- Own API contracts, data models, and inter-service communication
- Implement async processing, background jobs, and event-driven workflows Scalability, Reliability & Observability
- Design systems for horizontal scaling, high availability, and fault tolerance
- Identify and resolve performance bottlenecks across services and data stores
- Implement resilience patterns (timeouts, retries, idempotency, circuit breaking)
- Define and instrument monitoring and observability:
- Use observability data to debug production issues and drive system improvements Data, AI & Integrations
- Work with MongoDB for document modeling, indexing, and performance tuning
- Use Neo4j for graph-based data modeling and traversal
- Build backend workflows supporting RAG/RCA/Knowledge Graphs.
- Integrate backend systems with LLMs and observability tools like Langfuse
- Build and maintain enterprise integrations (Gmail, SharePoint, Drive etc.) Deployment & Operations
- Ensure services operate reliably across cloud and on-prem enterprise environments
- Support configuration management, environment isolation, and rollout strategies
- Collaborate on CI/CD and production readiness (with DevOps support) Must-Have Skills
- 4–6 years of backend engineering experience
- Strong proficiency in Python/Nodejs and modern async frameworks
- Hands-on experience with microservices architectures and distributed systems fundamentals
- Any one of the Cloud Services Knowledge i.e AWS/GCP/Azure.
- Experience with monitoring and observability
- Strong experience with MongoDB Strong Plus
- Experience with Neo4j or graph databases
- Exposure to LLMs, RAG pipelines, embeddings, or GenAI systems
- Familiarity with Langfuse or similar LLM observability tools
- Experience supporting on-prem or hybrid deployments
- Startup experience with ownership of production systems