LLM Engineer with AI and PYthon

Generative AI Engineer (Hybrid, India)
A fast-growing provider in the Enterprise Software & Artificial Intelligence services sector, we architect and deliver production-ready large-language-model platforms, data pipelines, and intelligent assistants for global customers. Our cross-functional squads blend deep ML expertise with robust engineering practices to unlock rapid business value while maintaining enterprise-grade security and compliance.Role & Responsibilities

• Design, build, and optimise end-to-end LLM solutions covering data ingestion, fine-tuning, evaluation, and real-time inference.
• Develop Python micro-services that integrate LangChain workflows, vector databases, and tool-calling agents into secure REST and gRPC APIs.
• Implement retrieval-augmented generation (RAG) pipelines, embedding models, and semantic search to deliver accurate, context-aware responses.
• Collaborate with data scientists to productionise experiments, automate training schedules, and monitor drift, latency, and cost.
• Harden deployments through containerisation, CI/CD, IaC, and cloud GPU orchestration on Azure or AWS.
• Contribute to engineering playbooks, mentor peers, and champion best practices in clean code, testing, and observability.
  

Skills & Qualifications

Must-Have

• 3-6 years Python backend or data engineering experience with strong OO & async patterns.
• Hands-on building LLM or GenAI applications using LangChain/LlamaIndex and vector stores such as FAISS, Pinecone, or Milvus.
• Proficiency in prompt engineering, tokenisation, and evaluation metrics (BLEU, ROUGE, perplexity).
• Experience deploying models via Azure ML, SageMaker, or similar, including GPU optimisation and autoscaling.
• Solid grasp of MLOps fundamentals: Docker, Git, CI/CD, monitoring, and feature governance.
  

Preferred

• Knowledge of orchestration frameworks (Kubeflow, Airflow) and streaming tools (Kafka, Kinesis).
• Exposure to transformer fine-tuning techniques (LoRA, PEFT, quantisation).
• Understanding of data privacy standards (SOC 2, GDPR) in AI workloads.
  

Benefits & Culture Highlights

• Hybrid work model with flexible hours and quarterly in-person sprint planning.
• Annual upskilling stipend covering cloud certifications and research conferences.
• Collaborative, experimentation-driven culture where engineers influence product strategy.
  

Join us to turn breakthrough research into real-world impact and shape the next generation of intelligent software.
Skills: git,monitoring,oo patterns,ci/cd,llamaindex,python,feature governance,evaluation metrics (bleu, rouge, perplexity),faiss,prompt engineering,cloud,prompt engg,azure ml,agent framework,async patterns,gen ai,langchain,tokenisation,docker,sagemaker,vectordb,milvus,pinecone