AI Engineer

About the Role

We are looking for a Senior AI Engineer (Backend) to build and scale the core backend systems for an enterprise conversational AI platform. The role focuses on designing reliable APIs, managing conversational state, integrating AI services, and ensuring security, auditability, and performance at scale. You will work closely with UI, SDK, and AI teams to deliver a backend that supports dynamic, multimodal, and highly personalized user interactions in a regulated NBFC environment.

Key Responsibilities

Backend Development & API Design

• Design and develop backend services to support conversational workflows and AI-driven user journeys.
• Build APIs for managing sessions, conversational state, user context, and capability flags.
• Integrate backend systems with LLM services, vector databases, and internal enterprise APIs.
• Ensure backend services support multimodal inputs and outputs (text, voice, image, file).

Architecture & System Design

• Contribute to the design of modular, scalable, and extensible backend architectures.
• Implement configuration-driven approaches over hardcoded business logic wherever possible.
• Ensure clean separation between orchestration logic, business rules, and infrastructure concerns.
• Support channel-aware behavior for mobile SDK and web environments.

Performance, Security & Reliability

• Optimize backend services for low latency and high throughput.
• Implement secure data handling, PII masking, and access controls.
• Ensure proper error handling, retries, and graceful degradation.
• Design systems with high availability, backup, and disaster recovery considerations.

Audit, Analytics & Observability

• Implement audit logging for all user actions and system decisions.
• Integrate analytics events to support product insights and monitoring.
• Ensure traceability of user intents, decisions, and backend responses.
• Support monitoring, alerting, and production issue diagnosis.

Collaboration & Delivery

• Work closely with frontend, SDK, and AI teams to align backend contracts and schemas.
• Participate in code reviews, design discussions, and technical planning.
• Contribute to CI/CD pipelines and production deployments.

Key Decisions / Dimensions

Backend & API Decisions

• Defining API contracts for conversational state, UI schemas, and capability flags.
• Choosing data models and storage strategies for session and journey state.
• Deciding synchronous vs asynchronous processing for AI and backend integrations.
• Determining retries, timeout, and fallback strategies for external dependencies.

Architecture & Performance Decisions

• Selecting appropriate caching, persistence, and messaging mechanisms.
• Deciding how to scale backend services for peak load and concurrency.
• Making trade-offs between performance, consistency, and complexity.
• Ensuring all backend features support feature enable/disable and rollback.

Security & Reliability Decisions

• Deciding what data is stored, logged, masked, or excluded.
• Implementing access controls and validation for all inbound requests.
• Ensuring services meet availability, backup, and recovery requirements.

Major Challenges

• Managing conversational state and context across long-running, multi-step user interactions.
• Supporting low-latency responses while integrating multiple internal and external systems.
• Designing backend systems that work consistently across trusted (mobile SDK) and untrusted (web) channels.
• Ensuring security, auditability, and compliance in a highly regulated environment.
• Handling evolving AI behaviours without breaking backend contracts or user journeys.
• Maintaining system stability while the platform rapidly evolves.

Qualifications

Required Qualifications and Experience

• Bachelor’s degree in computer science, Engineering, or related field.

Technical Skills

• Strong proficiency in Python, LangChain, LangGraph, Node.js for backend and AI service development.
• Hands-on experience building agentic systems and AI orchestration workflows.
• Experience designing APIs using REST and/or GRPC, including streaming APIs for real-time conversational flows.
• Expertise in prompt engineering, structured system instructions, and response control for LLMs.
• Experience managing session and context state for multi-step, conversational workflows.
• Hands-on experience with PostgreSQL, Redis, and other persistent or in-memory stores for session, embeddings, and caching.
• Experience integrating AI/ML platforms, vector databases, and other external services.
• Ability to design scalable backend solutions to support high concurrency, low-latency, multimodal AI interactions.
• Familiarity with cloud platforms, containerized deployments (Docker/Kubernetes), and serverless architectures.

Performance, Security & Quality

• Experience optimizing backend performance for AI pipelines, including concurrency, streaming, and memory usage.
• Strong understanding of secure coding practices, data privacy, and compliance (PII masking, audit logging).
• Experience implementing observability: logging, metrics, tracing, and alerting for AI workflows.
• Familiarity with CI/CD pipelines, automated testing, and production deployment best practices.
• Experience implementing fallback strategies, retries, and graceful degradation for AI/LLM services.