Software Developer / Application Developer

JD – APP DEVELOPER

About the Role

We are looking for an AI/LLM & App Development Engineer who can design, build, and integrate next-generation AI features into our application ecosystem. The role involves working hands-on with Generative AI models, building RAG (Retrieval-Augmented Generation) systems, developing scalable backend APIs, and managing structured + vector data pipelines.

This position is ideal for someone who loves solving complex problems, working with the latest AI technologies, and building production-ready architectures.

Key Responsibilities1. AI / LLM Development

• Develop and integrate Generative AI features using OpenAI, Gemini, Claude, and other LLM APIs.

• Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, and retrieval layers.

• Implement and manage vector embeddings, semantic search, and similarity scoring.

• Fine-tune model prompts, create system instructions, and optimize response quality.

• Conduct POCs for new AI use cases and convert them into production-ready modules.

2. Backend Engineering & API Integration

• Build and maintain backend services using Node.js (Express/NestJS).

• Connect AI modules with core application logic, authentication systems, and user workflows.

• Ensure backend scalability, error handling, performance tuning, and API security.

• Integrate third-party APIs and manage server-side automation tasks.

• Collaborate with frontend/mobile teams to support new feature rollouts.

3. Database & Vector Data Management

• Design and maintain MySQL database structures and optimise complex SQL queries.

• Implement and manage vector search, using Pinecone / FAISS / pgvector / Milvus (or similar).

• Store, index, and retrieve embeddings efficiently for AI workflows.

• Build data ingestion pipelines for clean and structured data flow.

• Ensure data quality, consistency, and compliance in all AI pipelines.

Required Skills & Qualifications

• Strong hands-on experience with Node.js, Express/NestJS.

• Good understanding of LLMs, embeddings, RAG architecture, and vector search.

• Experience with relational databases like MySQL, and optionally vector DBs.

• Familiarity with OpenAI, Google Gemini, or Anthropic Claude APIs.

• Understanding of authentication frameworks (JWT, OAuth) and API security.

• Ability to write clean code, follow best practices, and document workflows.

Nice to Have (Preferred Skills)

• Experience with FAISS, Pinecone, Milvus, pgvector, or any vector database.

• Exposure to NLP libraries (LangChain, LlamaIndex, Transformers).

• Knowledge of cloud platforms: AWS, GCP, Azure.

• Familiarity with microservices, queues, and event-driven architecture.

• Experience building production-grade AI features or chatbots.

Soft Skills

• Strong problem-solving mindset and curiosity about new AI technologies.

• Ability to collaborate with cross-functional teams (frontend, product, design).

• Good communication skills and willingness to experiment and iterate fast.

Education

• Bachelor’s degree in Computer Science, Engineering, AI/ML, or related fields.

• Equivalent experience also considered.

What We Offer

• Opportunity to build cutting-edge AI features in a real product environment.

• Fast-paced, innovative culture with room for experimentation.

• Career growth into AI/ML engineering or full-stack leadership roles.

Job Types: Full-time, Permanent

Benefits:

• Health insurance

• Paid sick time

• Paid time off

• Work from home

Work Location: In person

• It is a Full Time ఐటి / సాఫ్ట్వేర్ / డేటా విశ్లేషక job for candidates with 1 - 3 years of experience.