Software Application Engineer – AI & LLM
Core
Design, build, and deploy intelligent applications leveraging Large Language Models (LLMs), generative AI tools, and advanced data architectures to solve real-world problems.
Role type
Software Application Engineer specializing in AI & LLMs
Builds
Scalable, production-grade AI-powered applications, microservices, and API integrations
Domain
Artificial Intelligence / Large Language Models / Software Engineering
Deliverable
production ML models
Required skills
Python, TypeScript, JavaScript, Go, C++, LLM APIs, LangChain, LlamaIndex, function calling, prompt orchestration, vector databases, relational/NoSQL databases, AWS, GCP, Azure, Docker, Kubernetes, CI/CD
Preferred skills
Fine-tuning open-source LLMs (LoRA, QLoRA), model hosting frameworks (vLLM, Ollama, Hugging Face), AI safety guardrails, agentic architectures (AutoGPT, CrewAI, LangGraph)
Technologies
LangChain, LlamaIndex, Pinecone, Weaviate, Qdrant, Chroma, Ragas, LangSmith, PostgreSQL, Redis, MongoDB, vLLM, Ollama, Hugging Face, AutoGPT, CrewAI, LangGraph
Responsibilities
Design and maintain scalable AI-powered applications and microservices; Implement state-of-the-art LLMs using various frameworks; Architect and optimize RAG pipelines and vector databases; Design, test, and optimize prompt strategies and agentic workflows; Monitor, evaluate, and fine-tune model outputs for performance and cost; Partner with product managers and data science teams to translate business requirements into software features
Seniority
Mid-level (3+ years total, 1-2 years in AI/LLMs)
