Develop and optimize large language model applications at APPIT Software in Bangalore, building intelligent text generation, summarization, and conversational AI systems for enterprise clients.
Bangalore, India
Full-time
AI & Machine Learning
Responsibilities
Build and integrate LLM-powered features into enterprise applications
Optimize LLM inference performance through quantization, caching, and batching strategies
Develop custom prompt templates and chain-of-thought reasoning workflows
Implement structured output parsing and validation for reliable LLM responses
Evaluate and benchmark different LLM providers for cost, quality, and latency trade-offs
Build LLM-powered data extraction and document understanding pipelines
Requirements
3-5 years of software engineering experience with strong ML fundamentals
Hands-on experience with LLM APIs (OpenAI, Anthropic, Google Gemini, or open-source models)
Strong understanding of transformer architecture and tokenization
Experience with LLM serving frameworks (vLLM, TGI, or Ollama)
Proficiency in Python and experience with async programming patterns
Knowledge of embedding models and semantic search techniques
Nice to Have
Experience with open-source LLMs (Llama, Mistral, Qwen)
Knowledge of model distillation and compression
Familiarity with LLM evaluation frameworks (HELM, lm-eval)