LLM Software Developer - Python

Description

We are seeking a Software Developer - Large Language Models (LLMs) with strong hands-on experience in designing, building, and deploying AI-driven applications.

The ideal candidate will be passionate about leveraging cutting-edge generative AI technologies to create intelligent systems capable of understanding, generating, and reasoning with natural language.

You will collaborate closely with product managers, data scientists, and backend engineers to prototype, fine-tune, and productionize AI-powered solutions that drive automation, enhance user engagement, and deliver measurable business outcomes.

Key Responsibilities

• Design, develop, and deploy AI systems and applications powered by advanced LLMs such as GPT, Claude, Gemini, and LLaMA.
• Build APIs, data pipelines, and integration layers connecting model inference with real-time or enterprise data systems.
• Fine-tune and optimize models for specific domains, tasks, or conversational workflows using advanced training and evaluation techniques.
• Engineer prompts and response frameworks to improve contextual reasoning, factual accuracy, and alignment with business use cases.
• Implement retrieval-augmented generation (RAG) systems using vector databases such as Pinecone, Weaviate, FAISS, or Chroma.
• Develop and maintain AI services for summarization, classification, recommendation, and information extraction.
• Collaborate cross-functionally with frontend and backend teams to embed LLM-based capabilities into digital products and platforms.
• Monitor, evaluate, and iterate on model performance using feedback loops, telemetry, and A/B testing frameworks.
• Maintain code quality, documentation, and observability standards throughout the AI system lifecycle.
  
  

• Programming Expertise : Strong proficiency in Python and frameworks such as FastAPI, Flask, or Django for building production-grade APIs.
• LLM Experience : Hands-on exposure to OpenAI, Anthropic, Google Gemini, Hugging Face, or similar APIs.
• AI Workflow Tools : Experience with LangChain, LlamaIndex, or equivalent orchestration and agent frameworks.
• RAG & Embeddings : Proficient in designing retrieval pipelines and working with embedding models for contextual data augmentation.
• Vector Databases : Practical knowledge of Pinecone, Chroma, Weaviate, FAISS, or other vector search technologies.
• ML Fundamentals : Understanding of transformer architectures, tokenization, and model fine-tuning techniques.
• Cloud & Deployment : Experience with AWS, GCP, Azure, or Vercel for scalable deployment of AI workloads.
• Version Control & CI/CD : Familiarity with Git, Docker, and CI/CD pipelines for model and service deployment.
• Strong debugging, documentation, and collaboration abilities within agile environments.
  
  

• Experience in custom model training or distillation for specialized tasks.
• Exposure to knowledge graphs, data indexing, or hybrid retrieval approaches.
• Familiarity with MLOps or AI observability tools (Weights & Biases, MLflow, LangFuse).
• Contributions to open-source LLM or LangChain projects