Senior GenAI Engineer

• Build production LLM applications (GPT-4, Claude, Gemini, Llama, Mistral).
• Design RAG systems: semantic search, chunking, reranking, hybrid retrieval.
• Develop multi-agent systems, function calling, and agentic workflows.
• Implement advanced prompt engineering (zero-shot, few-shot, CoT, ReAct).

• Fine-tune LLMs using LoRA, QLoRA, PEFT, instruction tuning, RLHF, DPO.
• Optimize inference: quantization, pruning, distillation, caching.

• Build end-to-end LLM pipelines: versioning evaluation deployment monitoring.
• Orchestrate workflows using LangChain, LangGraph, LlamaIndex, CrewAI, Semantic Kernel.
• Implement MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocols.
• Multi-LLM routing, semantic caching, and cost optimization.

• Build vector databases (Pinecone / FAISS / Chroma DB etc.).
• Design embedding pipelines (OpenAI, Cohere, sentence-transformers).

• Implement guardrails: content moderation, prompt injection prevention, PII detection.
• Build evaluation frameworks with LLM-as-judge and human feedback loops.
• Monitor via LangSmith, Phoenix, Arize: latency, cost, quality, hallucinations.

• Strong hands-on experience with an ability to lead a team

Disclaimer: The job location mentioned in this description is based on publicly available information or company headquarters. Candidates are advised to verify the exact job location directly with the employer before applying.