Pirllabs
Website:
pirllabs.com
Job details:
We’re looking for a Gen AI Engineer to build and deploy AI systems powered by Large Language Models (LLMs). You’ll work on AI agents, RAG pipelines, workflow orchestration, and scalable AI infrastructure for real-world applications.
This role is ideal for engineers with strong Python skills, solid CS fundamentals, and hands-on experience building production AI systems.
Key Responsibilities· Fine-tune and optimize open-source LLMs.
· Build RAG pipelines and semantic search systems.
· Work on prompt engineering, evaluation, and inference optimization.
· Deploy scalable AI applications .
· Improve inference performance, reliability, and monitoring.
· Build backend APIs and production-ready AI services.
Required Skills & ExperienceEducation· B.Tech / M.Tech in Computer Science, AI, Information Science, Mathematics, or related fields.
Experience· 2–3 years of software engineering or ML engineering experience.
· Experience building and deploying production AI/ML systems.
Technical Skills· Strong Python programming skills.
· Good understanding of data structures, algorithms, and system design.
· Experience with PyTorch, TensorFlow, or JAX.
· Understanding transformers and LLM ecosystems.
· Experience with fine-tuning methods like LoRA, QLoRA, or PEFT.
· Experience building RAG systems and vector search pipelines.
· Familiarity with LangChain, LangGraph, CrewAI, AutoGen, or similar frameworks.
· Knowledge of Docker, Kubernetes, CI/CD, and model serving tools like vLLM or Triton.
· Experience building APIs using FastAPI or Flask.
Nice to Have· Experience with distributed training or inference.
· Familiarity with vector databases like Pinecone, Weaviate, ChromaDB, or Milvus.
· Experience with AI observability and monitoring tools.
· Open-source contributions or research experience
· Strong competitive programming or systems fundamentals.
Click on Apply to know more.