Generative AI Engineer
NLB Services
Mandatory LLM Experience: 2+ years of hands-on development Core Skills: Python, LLMs, RAG, LangChain/LangGraph, FastAPI, OpenAI APIs Role Type: Backend Engineering / Generative AI Job Summary We are looking for an experienced Senior Python GenAI Engineer with strong production-grade Python development skills and hands-on experience building, deploying, and maintaining LLM-powered applications. The ideal candidate will have expertise in Retrieval-Augmented Generation (RAG), LLM orchestration frameworks, asynchronous APIs, and scalable distributed systems. Key Responsibilities Design, develop, and maintain production-grade Python applications and backend services. Build and optimize LLM-powered applications using LangChain, LangGraph, or equivalent frameworks. Develop end-to-end RAG pipelines, including document ingestion, chunking, embeddings, vector search, reranking, and answer generation. Integrate OpenAI APIs, including Chat Completions, Responses API, streaming, and tool/function calling. Implement prompt engineering techniques, including system prompts, few-shot prompting, and structured JSON outputs. Develop asynchronous services using Python asyncio, httpx, and FastAPI. Build resilient services using circuit breakers, retries, timeouts, and appropriate error-handling mechanisms. Design and maintain PostgreSQL databases using SQLAlchemy Async and Alembic migrations. Design scalable microservices, distributed systems, and RESTful APIs. Containerize applications using Docker and support deployments in Kubernetes environments. Collaborate with engineering, product, and AI teams to deliver reliable, secure, and scalable GenAI solutions. Follow Git-based development practices and CI/CD workflows. Monitor, troubleshoot, and optimize application performance, latency, reliability, and LLM usage costs. Mandatory Technical Skills 8–10 years of software development experience. Strong Python programming expertise in production environments. At least 2 years of hands-on LLM application development experience. Experience with LangChain, LangGraph, or equivalent LLM frameworks. Strong understanding of RAG architecture, embeddings, vector databases/search, reranking, and answer generation. Experience integrating OpenAI APIs, streaming responses, and tool calling. Hands-on experience with FastAPI, asyncio, and httpx. Strong prompt engineering and structured output experience. Experience with PostgreSQL, SQLAlchemy Async, and Alembic. Knowledge of resilient service design, retries, timeouts, and circuit breaker patterns. Strong system design, microservices, distributed systems, and API design skills. Working knowledge of Git, CI/CD, Docker, and Kubernetes basics. Preferred Qualifications Experience deploying LLM applications in production. Understanding of RAG evaluation, retrieval quality, hallucination reduction, and observability. Experience with vector databases such as pgvector, Pinecone, Weaviate, or Qdrant. Knowledge of LLM security, access control, and prompt injection mitigation. Experience optimizing inference latency, token usage, and application scalability.
This job was verified from LinkedIn Jobs US. Applications are completed on the original source.
Apply on the original listing ↗
Something wrong with this job?
Own this listing? Ask us to remove it