Role: Generative AI Engineer
Location: Newark,NJ
Duration: Long term contract
JD: Generative AI Engineer:
Semantic Search & LLM Platforms Job Summary We are looking for a Generative AI Engineer to design, build, and scale an enterprise AI-powered semantic search platform for API discovery and knowledge retrieval.
The role focuses on developing LLM-driven search, RAG pipelines, and cloud-native AI services that enable natural language interaction with large-scale technical repositories.
The ideal candidate has strong hands-on experience with LLMs, embeddings, vector databases, FastAPI microservices, and multi-cloud AI deployments, and is passionate about building reliable, production-grade GenAI systems.
Key Responsibilities
Design and implement AI-powered semantic search solutions for large-scale API and technical documentation repositories.
Develop Retrieval-Augmented Generation (RAG) pipelines using OpenAI embeddings, LangChain, LangGraph, and vector databases (FAISS, pgvector).
Build and maintain FastAPI-based microservices for LLM-powered search, summarization, and inference with secure authentication (JWT).
Create and manage data ingestion and indexing pipelines, including document chunking, metadata extraction, embedding generation, and vector refresh workflows. Implement multi-cloud LLM integration and routing across Azure OpenAI, AWS Bedrock, and GPT-4 with fault-tolerant fallback mechanisms.
Apply grounding techniques and hallucination mitigation strategies to improve response accuracy and reliability.
Define and track RAG and LLM evaluation metrics such as precisionk, grounding score, latency, and hallucination rate. Integrate monitoring, logging, and observability using LangSmith and OpenTelemetry for model performance and system health.
Deploy and scale AI services using cloud-native architectures (AWS Lambda, ECS Fargate, API Gateway, DynamoDB, S3).
Collaborate with UI/UX and platform teams to deliver intuitive interfaces for natural-language API discovery.
Contribute to CI/CD pipelines to enable automated testing, deployment, and versioning of AI services.
Required Skills & Qualifications Technical Skills Programming:
Python APIs & Services: FastAPI, REST APIs, JWT authentication
Generative AI & LLMs: GPT-4, OpenAI embeddings, LangChain, LangGraph, RAG architectures
Vector Databases: FAISS, pgvector Cloud Platforms: AWS (Lambda, ECS Fargate, API Gateway, DynamoDB, S3), Azure OpenAI, AWS Bedrock
AI Evaluation & Observability: LangSmith, OpenTelemetry, RAG evaluation metrics
DevOps & CI/CD: Docker, CI/CD pipelines, cloud-native deployments.
Experience Hands-on experience building production-grade GenAI or semantic search systems Experience working with large-scale document or API repositories Strong understanding of LLM reliability, grounding, and hallucination control Experience deploying and operating AI systems in cloud environments Preferred Qualifications Experience designing enterprise knowledge search or developer productivity platforms Familiarity with multi-cloud AI architectures Exposure to agent-based LLM workflows Experience mentoring or providing technical guidance to other engineers