Job Overview
Role: Software Development Engineer Intern – Backend Location: Bengaluru, Karnataka, India Experience: 0 – 1 Years / Entry Level (Pre-final and final-year students) Qualification: B.E / B.Tech / M.E / M.Tech / MCA or equivalent Key Skills: Data Structures and Algorithms, Backend programming (Python, Java, Go, Node.js), REST/gRPC APIs, SQL, Databases, Distributed systems, Caching, Kafka, GenAI, LLM applications, RAG, Vector databases, Cloud, Containers
Job Description
This internship is for a Software Development Engineer Intern – Backend in Bengaluru, part of the Engineering team working with PulseAI Research, Smytten's AI-powered consumer intelligence platform. Designed for pre-final and final-year students, the role provides hands-on exposure to backend engineering, AI-powered applications, APIs, microservices, distributed systems, GenAI, LLM integrations, RAG pipelines, and cloud-native development. The in-office internship has an expected duration of 4–6 months, requiring availability for the full period for potential PPO consideration.
Roles and Responsibilities
- System Design & Build: Design and build scalable, secure and fault-tolerant backend systems.
- AI Workflow Orchestration: Develop orchestration layers for AI and agentic workflows; connect LLMs, analytical models, data sources, research engines and enterprise applications.
- API & Microservices: Develop high-performance APIs and microservices.
- Asynchronous Processing: Build asynchronous processing systems for AI-led analytics and research workflows.
- GenAI Infrastructure: Develop backend infrastructure for GenAI applications; work with model gateways, prompt orchestration, structured outputs and AI workflows; build and support RAG pipelines, embeddings, vector retrieval, caching and AI guardrails.
- Data Processing: Build systems capable of processing structured and unstructured data.
- Architecture Support: Support multi-tenant enterprise architecture with data isolation and access controls.
- Workflow Engines: Develop workflow engines involving queues, retries, scheduling and distributed tasks.
- Production Integration: Integrate large language models and machine-learning models into production systems; work on latency, reliability, observability and model fallback mechanisms.
- AI Quality: Support AI explainability and auditability through source-to-output lineage.
- Collaboration & Research: Collaborate with AI/ML engineers, data scientists, researchers and product teams; evaluate emerging developments in LLMs, AI agents, retrieval systems and data infrastructure.
Skills and Eligibility Criteria
Educational Background: Pre-final or final-year student pursuing B.E., B.Tech, M.E., M.Tech, MCA or equivalent.
Experience: 0–1 Years / Entry Level. Must be available for a full-time 4–6 month internship (at least 4 months for potential PPO).
Mandatory Technical Skills:
- Strong fundamentals in Data Structures and Algorithms
- Good understanding of Operating Systems and Databases
- Knowledge of backend development using Python, Java, Go, Node.js or an equivalent technology
- Understanding of REST or gRPC APIs
- Basic understanding of distributed systems concepts
- Knowledge of SQL and modern database architectures
- Understanding of caching, queues and asynchronous processing
- Basic familiarity with cloud-native application development
Competencies:
- Prior internships, personal projects or open-source contributions are advantageous
- Practical exposure to LLM APIs and Generative AI applications (Preferred)
- Agentic AI frameworks and workflow orchestration (Preferred)
- RAG pipelines, embeddings and vector databases (Preferred)
- Machine learning inference systems (Preferred)
- Large-scale data processing (Preferred)
- Kafka and event-driven architectures (Preferred)
- Redis, Elasticsearch or OpenSearch (Preferred)
- Docker and Kubernetes (Preferred)
- AWS, GCP or Azure (Preferred)
- Data warehouses (Preferred)
- Enterprise SaaS and multi-tenant architecture (Preferred)