Orion Innovation is a premier, award-winning, global business and technology services firm. Orion delivers game-changing business transformation and product development rooted in digital strategy, experience design, and engineering, with a unique combination of agility, scale, and maturity. We work with a wide range of clients across many industries including financial services, professional services, telecommunications and media, consumer products, automotive, industrial automation, professional sports and entertainment, life sciences, ecommerce, and education.
Job Overview:
We are seeking a seasoned AI Developer to lead the design and implementation of next-generation Agentic AI solutions. You won't just be building chatbots; you will be architecting autonomous systems where multiple specialized AI agents collaborate to solve complex, long-horizon business problems. You will leverage a multi-cloud strategy to deploy scalable, resilient, and "reasoning-heavy" AI workflows.
Key Responsibilities
- Agentic Architecture: Design and develop autonomous agents capable of independent planning, tool-use (function calling), context & prompt engineering, and self-correction.
- Multi-Agent Orchestration: Implement LangGraph to manage task delegation, conflict resolution, and collaborative reasoning between specialized agents.
- Advanced RAG & Memory: Build sophisticated Retrieval-Augmented Generation (RAG) pipelines with episodic and semantic memory to ensure agents maintain context over long interactions.
- Cloud-Native Deployment: Architect and deploy AI services across AWS (Bedrock/SageMaker), Azure (OpenAI Service/Foundry), ensuring high availability and cost optimization.
- Guardrails & Ethics: Implement rigorous evaluation frameworks (e.g., Ragas, TruLens) and safety guardrails to prevent hallucinations and ensure responsible agent behavior.
- Performance Tuning: Optimize LLM latency and throughput using techniques like prompt caching, quantization, and specialized model routing.
- Prompt engineering & Context engineering.
Key Skills:
- Core AI: 4+ years of professional experience in AI/ML, with at least 1.5+ years focused specifically on Generative AI and LLM orchestration.
- Agent Frameworks: Hands-on expertise with LangGraph. Proven ability to build "loops" and "state machines" rather than just linear chains.
- Programming: Mastery of Python (Asyncio, Pydantic, FastAPI). Experience with TypeScript/Node.js is a significant plus.
- Cloud Infrastructure:
- AWS: Bedrock, Lambda, Step Functions, S3.
- Azure: Azure OpenAI, AI Search, CosmosDB, PostgreSQL.
- Data & Memory: Proficiency with Vector Databases like Pinecone, Weaviate, Milvus, or pgvector. Understanding of graph databases (Neo4j) for knowledge-graph-enhanced RAG.
- DevOps/AIOps: Experience with Docker, Kubernetes, and CI/CD pipelines specifically for AI (LLMOps).
Preferred Qualifications
- Contributions to open-source AI frameworks or research publications in MAS.
- Experience with Model Context Protocol (MCP) or Agent-to-Agent (A2A) communication standards.
- Familiarity with fine-tuning techniques (LoRA, QLoRA) for specialized agent tasks.
Orion is an equal opportunity employer, and all qualified applicants will receive consideration for employment without regard to race, color, creed, religion, sex, sexual orientation, gender identity or expression, pregnancy, age, national origin, citizenship status, disability status, genetic information, protected veteran status, or any other characteristic protected by law.
Candidate Privacy Policy
Orion Systems Integrators, LLC and its subsidiaries and its affiliates (collectively, “Orion,” “we” or “us”) are committed to protecting your privacy. This Candidate Privacy Policy (orioninc.com) (“Notice”) explains:
- What information we collect during our application and recruitment process and why we collect it;
- How we handle that information; and
- How to access and update that information.
Your use of Orion services is governed by any applicable terms in this notice and our general Privacy Policy.
