Senior Staff Engineer - Python Backend & LLM

A Top Tier IT MNC is hiring for Senior Staff Engineer - Python Backend & LLM.

Experience: 7 - 11 years

Mandatory Skills : FastAPI (Expert),LLM Application Frameworks (Strong),Prompt Engineering with LLMs (Strong),Python (Strong)

Job Summary

We are looking for a highly skilled LLM Engineer & Python Backend Developer to build, scale, and maintain AI-powered applications using Large Language Models and modern Python backend systems. You will be responsible for developing intelligent agents, RAG pipelines, and production-grade APIs that power next-generation AI products.

Key Responsibilities

LLM, AI & GenAI Engineering

Design, implement, and optimize applications using LLMs (GPT-4/5, Claude, Gemini, LLaMA, Mistral, Mixtral, DeepSeek, etc.).

Develop advanced prompt engineering, system prompting, and structured output pipelines.

Build and maintain RAG (Retrieval-Augmented Generation) systems with hybrid search.

Implement multi-agent systems and autonomous workflows.

Fine-tune and adapt foundation models using LoRA, QLoRA, PEFT, and adapters.

Deploy open-source LLMs using vLLM, TGI, Ollama, LM Studio, or Triton.

Integrate multimodal models (text, image, audio, video).

Develop evaluation pipelines for hallucination detection, factuality, and bias.

Implement guardrails, moderation, and alignment techniques.

Optimize latency, cost, and throughput for LLM inference.

Backend Engineering (Python)

Build scalable backend systems using FastAPI, Django, or Flask.

Design REST, GraphQL, and streaming APIs.

Develop microservices and event-driven architectures.

Integrate relational, NoSQL, and in-memory databases.

Implement authentication, authorization, and security best practices.

Write unit, integration, and load tests.

Optimize backend performance and observability.

AI Infrastructure & LLMOps

Design model serving and inference pipelines.

Build monitoring, logging, and tracing for AI systems.

Implement CI/CD pipelines for ML/LLM workflows.

Manage feature stores, embedding pipelines, and indexing.

Handle versioning for models, prompts, and datasets.

Implement A/B testing for AI outputs.

Automate retraining and evaluation pipelines.

Data, Search & Knowledge Systems

Build document ingestion, chunking, and preprocessing pipelines.

Implement semantic, keyword, and hybrid search.

Work with vector databases (Pinecone, Weaviate, Milvus, Qdrant, FAISS, Chroma).

Develop knowledge graphs and ontology-based systems.

Build enterprise search and document intelligence systems.

Cloud, DevOps & Scalability

Deploy AI systems on AWS, GCP, or Azure.

Manage Kubernetes-based inference clusters.

Optimize GPU/TPU utilization.

Implement autoscaling and cost optimization.

Secure AI pipelines and infrastructure.

Required Qualifications

Bachelor’s/Master’s degree in CS, AI, Data Science, or equivalent experience.

Strong proficiency in Python.

Proven experience with LLM APIs and open-source models.

Hands-on experience with RAG, embeddings, and vector search.

Experience with AI frameworks (LangChain, LlamaIndex, Haystack, DSPy, AutoGen, CrewAI).

Experience building production backend systems.

Solid understanding of distributed systems and microservices.

Experience with cloud platforms and containerization