Backend Engineer – Generative AI (Infra)
We are seeking a talented Backend Engineer with a focus on AI-driven systems, particularly in developing and maintaining scalable infrastructures for Generative AI applications. This role requires a solid background in backend engineering, API design, and AI model integration, with experience in LLMs, diffusion models, and multimodal AI systems.
As a Backend Engineer, you will be responsible for building and managing backend systems that support AI services, ranging from model APIs to data retrieval pipelines, ensuring they are optimized for performance and security in production environments. Experience with enterprise-level systems, particularly in banking or financial services, is a significant advantage.
Key Responsibilities
Backend Architecture & Development
- Design and develop scalable backend services to support AI and Generative AI workloads.
- Build and optimize RESTful and GraphQL APIs for model inference, prompt processing, and data access.
- Create modular backend components for high-performance, scalable AI operations.
Generative AI Pipeline Integration
- Collaborate with AI engineers to integrate and deploy Generative AI models (LLMs, diffusion models, text-to-image, speech-to-text) in production.
- Implement retrieval-augmented generation (RAG) pipelines using vector databases like Pinecone, Weaviate, FAISS, or Milvus.
- Optimize AI model serving and inference with frameworks like TensorFlow Serving, TorchServe, FastAPI, or custom endpoints.
API Management & Optimization
- Develop secure APIs for AI-driven services, ensuring proper version control, authentication (OAuth2, JWT), and scalability.
- Integrate third-party AI APIs (OpenAI, Anthropic, Google Gemini, Stability AI) into internal systems.
- Monitor API usage, optimize for latency, and ensure high-throughput AI operations.
System & Environment Setup
- Set up backend environments using Docker, Kubernetes, and CI/CD pipelines for automated deployments.
- Manage scalable cloud environments (AWS, Azure, GCP) with load balancing and fault tolerance.
- Support development environments and backend utilities for cross-functional AI teams.
Performance & Security
- Optimize server performance for AI workloads through caching, queuing, and load balancing techniques.
- Ensure compliance with data privacy and security regulations, especially in financial domains.
- Implement observability tools like Prometheus, Grafana, and ELK Stack for performance monitoring.
Collaboration
- Collaborate with AI/ML engineers, data scientists, frontend developers, and DevOps teams.
- Contribute to architecture discussions, backend documentation, and process improvements.
- Participate in agile ceremonies, code reviews, and design sessions.
Required Technical Skills
Languages:
- Python (primary), Node.js, Java
Backend Frameworks:
- FastAPI, Flask, Django, Express.js, Spring Boot
AI & Generative Tools:
- Familiarity with LLMs (e.g., GPT, Claude, Gemini, LLaMA, Mistral)
- Experience with diffusion models (e.g., Stable Diffusion, Midjourney APIs)
- Knowledge of transformer models via Hugging Face or OpenAI APIs
- Understanding of prompt engineering and model-serving best practices
Databases:
- PostgreSQL, MongoDB, Redis, Elasticsearch
Vector Databases:
- Pinecone, Weaviate, Milvus, FAISS (for RAG systems)
Infrastructure & DevOps:
- Docker, Kubernetes, Jenkins, GitLab CI/CD, AWS Lambda, ECS, or GCP Cloud Run
Monitoring:
- Prometheus, Grafana, ELK Stack, New Relic
API Technologies:
- REST, GraphQL, gRPC
Preferred Qualifications
- Experience with AI product backend systems or enterprise software, especially in banking.
- Familiarity with AI pipeline orchestration tools (LangChain, LlamaIndex, Haystack).
- Understanding of model lifecycle management, vector embeddings, and inference scaling.
- Familiarity with data encryption, tokenization, and compliance standards (PCI DSS, ISO 27001).
Soft Skills
- Strong problem-solving and debugging abilities.
- Excellent communication skills for collaborating with cross-functional teams.
- High attention to detail and performance optimization.
- Curiosity and enthusiasm for emerging AI technologies and backend architecture.
Education
- Bachelor's or Master's degree in Computer Science, IT, AI, or a related field.
- Certifications in AI/ML, Cloud Architecture, or Backend Development are a plus.
Why Join Us
- Work at the forefront of backend engineering and Generative AI innovation.
- Build production-ready systems for large-scale, intelligent applications.
- Collaborate with a team pushing the boundaries of AI applications and infrastructure optimization.
Work Schedule
Working Days: Monday to Saturday (Alternate Saturdays leave)
Timings: 9:00 AM to 6:00 PM
