About the Role
Role details below.
Responsibilities
- Design, implement, and optimize LLM-powered applications using leading and open-source models.
- Develop advanced prompt engineering, system prompts, and structured output pipelines.
- Build RAG pipelines with hybrid search, embeddings, and custom retrieval strategies.
- Develop multi-agent systems and autonomous AI workflows.
- Fine-tune, adapt, and serve foundation models using LoRA/QLoRA and modern inference engines.
- Deploy and scale LLM workloads using vLLM, TGI, Ollama, or GPU/TPU-based systems.
- Integrate multimodal models across text, image, audio, and video.
- Build evaluation pipelines for hallucination detection, factual accuracy, quality scoring, and alignment.
- Implement guardrails, moderation, and safety policies for AI systems.
- Build scalable backend systems using FastAPI, microservices, event-driven architectures, and secure API frameworks.
- Optimize backend performance, observability, and reliability.
- Build ingestion pipelines for document processing, chunking, preprocessing, and semantic indexing.
- Implement semantic, vector, and hybrid search at scale.
- Deploy AI systems on cloud platforms, manage Kubernetes inference clusters, and optimize GPU utilization.
- Set up CI/CD, automated testing, model versioning, and production monitoring for AI workflows.
- Develop enterprise-grade search, knowledge systems, and document intelligence platforms.
- Ensure robustness, security, and scalability in all AI and backend systems.
- Stay updated with the latest GenAI, LLMOps, and backend engineering innovations and share knowledge within the technical community.
Requirements
- Total experience 7.5+ years
- Strong hands-on expertise in LLM engineering and Python backend development.
- Expertise in LLM Application Frameworks, Prompt Engineering with LLMs, Python, FastAPI
- Proven experience building and deploying applications using cutting-edge LLMs (GPT-4/5, Claude, Gemini, Mistral, LLaMA, Mixtral, DeepSeek, etc.).
- Strong experience with RAG pipelines, embeddings, prompt engineering, and multi-agent systems.
- Hands-on expertise with LLM frameworks such as LangChain, LlamaIndex, Haystack, DSPy, AutoGen, CrewAI.
- Deep knowledge of model fine-tuning techniques such as LoRA, QLoRA, PEFT, adapters.
- Experience deploying open-source LLMs using vLLM, TGI, Ollama, LM Studio, Triton, etc.
- Strong backend engineering experience with FastAPI (expert), Django or Flask, microservices, and distributed systems.
- Experience implementing REST, GraphQL, and streaming APIs.
- Hands-on experience with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, FAISS, Chroma.
- Knowledge of semantic search, hybrid search, embedding pipelines, and enterprise knowledge systems.
- Strong understanding of cloud platforms (AWS, GCP, Azure), containers, and Kubernetes.
- Experience with MLOps/LLMOps practices—CI/CD for ML workflows, monitoring, logging, tracing, and model lifecycle management.
- Bachelor’s/Master’s in CS, AI, Data Science, or equivalent experience.
- Excellent communication, collaboration, and problem-solving skills.
