GEN AI Developer

OP is looking for exceptional engineers who are excited about the rapidly evolving Generative AI ecosystem and want to build production-grade AI solutions that solve real enterprise problems. This is a hands-on engineering role focused on LLMs, RAG architecture, agentic AI, LangGraph, AWS GenAI services, Python, FastAPI, and vector databases. The ideal candidate will have a strong track record of taking Generative AI solutions from architecture and prototyping through production deployment, optimization, scalability, and support.  At OP, we are also investing in and building next-generation AI capabilities and in-house technology products that leverage Large Language Models, RAG, AI agents, and cloud-native architectures. This role provides an opportunity to work directly on an in-house AI product, helping shape its architecture, capabilities, scalability, and evolution from the ground up.
Key Responsibilities:

• Design, develop, and productionize LLM and Generative AI applications for an in-house AI product.
• Design and own scalable RAG architectures, including document ingestion, processing, chunking, embeddings, indexing, retrieval, reranking, context construction, and LLM generation.
• Build advanced agentic AI workflows using LangGraph, including state management, tool calling, workflow orchestration, multi-step reasoning, and human-in-the-loop capabilities.
• Develop high-performance backend services and APIs using Python and FastAPI.
• Build and integrate vector database and semantic search solutions for enterprise knowledge retrieval.
• Leverage AWS and Amazon Bedrock to build, deploy, scale, and operate production-grade GenAI applications.
• Evaluate and integrate different LLMs/foundation models based on quality, latency, cost, context requirements, and business use cases.
• Develop advanced prompt engineering, structured outputs, function/tool calling, and LLM evaluation capabilities.
• Improve RAG performance using hybrid search, query transformation, metadata filtering, reranking, contextual retrieval, and semantic chunking.
• Implement strategies to improve accuracy, grounding, relevance, and reduction of LLM hallucinations.
• Build reusable GenAI components and services that can scale across the product.
• Implement LLM observability, evaluation, monitoring, logging, and performance optimization.
• Optimize GenAI applications for latency, scalability, reliability, and cost.
• Work closely with product and engineering teams to translate business requirements into production-ready AI capabilities.
• Apply best practices for GenAI security, data privacy, access control, prompt-injection protection, and responsible AI.

Must Haves:

• 7+ years of software engineering experience with significant hands-on experience in AI/ML and Generative AI.
• 3+ years of hands-on experience building production-grade LLM/Generative AI applications.
• Strong hands-on experience designing and implementing RAG architecture from end to end.
• Extensive experience working with LLMs, foundation models, embeddings, prompt engineering, and LLM APIs.
• Strong hands-on experience with LangGraph and agentic AI workflow development.
• Expert-level Python development experience.
• Strong production experience developing APIs and microservices using FastAPI.
• Extensive hands-on experience with AWS, particularly AWS GenAI capabilities and Amazon Bedrock.
• Strong experience with vector databases and semantic/hybrid search.
• Experience deploying and supporting production GenAI applications in AWS/cloud environments.
• Strong understanding of LLM application architecture, RAG pipelines, retrieval strategies, embeddings, vector search, and model selection.
• Proven ability to take an AI solution from architecture development deployment production support.
• Strong software engineering fundamentals, including API design, testing, Git, CI/CD, logging, monitoring, and performance optimization.

Preferred Skills:

• Experience building enterprise AI products or internal AI platforms.
• Experience with LLM observability and evaluation frameworks.
• Experience with LangSmith or similar platforms.
• Experience with AI security, guardrails, PII protection, and prompt-injection mitigation.

Benefits:

• 401(k).
• Dental Insurance.
• Health insurance.
• Vision insurance.
• We are an equal-opportunity employer and value diversity, equality, inclusion, and respect for people.
• The salary will be determined based on several fa…