Note: The job is a remote job and is open to candidates in USA. Photon is seeking a Senior Agentic AI Engineer to design, build, deploy, and operate enterprise-grade AI agents and multi-agent systems. The role focuses on Generative AI, LLMs, agentic workflows, and AI orchestration, delivering scalable copilots and intelligent automation across various environments.
Responsibilities
- Design, develop, and deploy AI agents and multi-agent workflows using Python and agentic frameworks (e.g., LangChain, LangGraph, or equivalent)
- Build enterprise-scale RAG solutions over structured and unstructured data sources
- Develop agent orchestration workflows integrating models, tools, APIs, and enterprise services
- Build AI-powered copilots, assistants, and automation solutions for enterprise use cases
- Implement AI monitoring, observability, tracing, telemetry, and performance measurement
- Implement agent memory patterns (short-term, long-term, episodic)
- Integrate agents with enterprise platforms (APIs, databases, SharePoint, Confluence, Salesforce, knowledge repositories)
- Contribute to AI governance: guardrails, security controls, policy enforcement, and compliance
- Optimize prompts, reasoning strategies, workflows, and execution performance
- Collaborate with Data Science and ML teams on evaluation, optimization, and continuous improvement
Skills
- 5–10 years of software engineering experience with strong Python expertise
- 3+ years designing and implementing AI/ML solutions
- Hands-on experience building Generative AI applications using LLMs, RAG, and agentic frameworks (LangChain/LangGraph or equivalent; OpenAI SDK or similar)
- Experience delivering enterprise-grade AI solutions in production
- Experience with distributed onshore/offshore team delivery
- Solid API/service engineering fundamentals (REST/async services, integration patterns)
- Practical understanding of AI observability, evaluation, and production reliability
- Design, develop, and deploy AI agents and multi-agent workflows using Python and agentic frameworks (e.g., LangChain, LangGraph, or equivalent)
- Build enterprise-scale RAG solutions over structured and unstructured data sources
- Develop agent orchestration workflows integrating models, tools, APIs, and enterprise services
- Build AI-powered copilots, assistants, and automation solutions for enterprise use cases
- Implement AI monitoring, observability, tracing, telemetry, and performance measurement
- Implement agent memory patterns (short-term, long-term, episodic)
- Integrate agents with enterprise platforms (APIs, databases, SharePoint, Confluence, Salesforce, knowledge repositories)
- Contribute to AI governance: guardrails, security controls, policy enforcement, and compliance
- Optimize prompts, reasoning strategies, workflows, and execution performance
- Collaborate with Data Science and ML teams on evaluation, optimization, and continuous improvement
- Clear written and verbal communication with technical and business stakeholders
- Ability to own delivery end-to-end in a distributed team model
- Pragmatic trade-off judgment between speed, quality, cost, and governance
- Cloud AI platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI, or similar)
- Vector databases / search (pgvector, OpenSearch, Pinecone, Weaviate, or similar)
- LLMOps tooling (tracing, eval harnesses, prompt/version management)
- Enterprise integrations (SharePoint, Confluence, Salesforce)
- Containerized deployment practices (Docker; Kubernetes a plus)
- AI security, PII handling, and guardrail frameworks
Benefits
- Medical, vision, and dental benefits
- 401k retirement plan
- Paid time off
- Paid holidays
Company Overview
Company H1B Sponsorship