• Integrate Generative AI models, including LLMs, with external APIs, tools, and databases using secure and efficient orchestration patterns. • Design, develop, and deploy AI workflows and Agentic AI solutions, enabling the seamless orchestration of intelligent agents to plan and perform tasks while leveraging autonomous and/or human-in-the-loop paradigms. • Implement and optimize multi-agent systems, leveraging standards and protocols such as Model Context Protocol (MCP) and emerging frameworks for agent interoperability. • Develop evaluation frameworks, metrics, and checkpoints for agent autonomy, performance, and safety, ensuring compliance with moderation, security, and ethical standards. • Ensure robust AI agent operations by applying observability, monitoring, and MLOps best practices, facilitating reliable deployment pipelines and continuous performance optimization. • Collaborate closely with data experts, orchestrating AI model selection, tuning, and performance validation to meet specific agent-based application needs. • Communicate complex AI concepts, systems, and decisions effectively to technical and non-technical stakeholders, promoting transparency and trust in AI delivery.

• Integrate Generative AI models, including LLMs, with external APIs, tools, and databases using secure and efficient orchestration patterns. • Design, develop, and deploy AI workflows and Agentic AI solutions, enabling the seamless orchestration of intelligent agents to plan and perform tasks while leveraging autonomous and/or human-in-the-loop paradigms. • Implement and optimize multi-agent systems, leveraging standards and protocols such as Model Context Protocol (MCP) and emerging frameworks for agent interoperability. • Develop evaluation frameworks, metrics, and checkpoints for agent autonomy, performance, and safety, ensuring compliance with moderation, security, and ethical standards. • Ensure robust AI agent operations by applying observability, monitoring, and MLOps best practices, facilitating reliable deployment pipelines and continuous performance optimization. • Collaborate closely with data experts, orchestrating AI model selection, tuning, and performance validation to meet specific agent-based application needs. • Communicate complex AI concepts, systems, and decisions effectively to technical and non-technical stakeholders, promoting transparency and trust in AI delivery.

Role Description We are seeking a motivated and talented individual to join us for a 12-week summer internship within our Development department. This internship will focus on integrating AI tools (e.g., ChatGPT Enterprise / similar LLM platforms) into existing team workflows to reduce manual reporting effort, improve consistency, and accelerate market and project insights. Internships at esVolta aim to offer students industry exposure and hands-on experience. Core Responsibilities - Identify opportunities where AI can reduce effort and improve clarity in recurring stakeholder reporting. - Build a repeatable workflow that can support quarterly market reporting with minimal manual effort. - Prototype AI-driven checks to support QA/QC of budget files and submissions, including consistency checks, anomaly detection, and completeness reviews. - Perform due diligence on investment portfolios. - Craft detailed and informative presentations for management. Qualifications - Currently pursuing a bachelor’s or master’s degree in computer science, engineering, finance, economics, etc. - An interest in the energy sector and US power markets. - Strong analytical thinking and comfort working with ambiguous problems. - Effective communication (verbal, written, and presentation) skills. - Excellent analytical and quantitative skills. - Strong interpersonal skills with the ability to effectively work within multi-disciplinary project teams. - Strong organizational skills and attention to detail. - Experience using LLM tools (ChatGPT, Gemini, Claude, etc.) and interest in applying them to real business workflows. - Familiarity with basic automation concepts (APIs, integrations, workflow tools) and/or prompt engineering. Requirements - The hourly rate for this position is $30.00 per hour. - 40-hour work week. - Flexible; option to work-from-home with periodic office visits for in-person engagement or to work from company offices in Newport Beach. - Willingness to be remotely based and ability to travel to company offices and project sites. Benefits - esVolta is an Equal Opportunity Employer. - We celebrate all forms of diversity and are committed to creating an inclusive environment for all employees. - We ensure that individuals with disabilities are provided reasonable accommodation to participate in the hiring process, perform essential job functions, and receive other benefits and privileges of employment.

• Own end-to-end development of LLM features: problem framing, data prep, prototyping, offline/online evaluation, deployment, and monitoring. • Build retrieval-augmented generation (RAG) pipelines with vector search (e.g., FAISS, Pinecone, OpenSearch/KNN) and document orchestration. • Implement prompt strategies, tool use/function calling, and guardrails for safety, bias, and privacy. • Integrate models in production services (REST/GraphQL/gRPC), including auth, rate limiting, and observability. • Stand up evals and experiment frameworks (A/B tests, golden sets, regression suites) with clear success metrics. • Optimize for latency, cost, and quality: prompt compression, caching, model selection, fine-tuning/LoRA, distillation where appropriate. • Collaborate with DevOps/MLOps/Platform to automate CI/CD, data/version management, and feature flags. • Embed with CX/Support to mine tickets, chats, and call transcripts; convert VOC into training/eval datasets and backlog priorities. • Instrument user journeys and define online/offline evals (win rate, hallucination rate, TTR, CSAT/NPS); run A/B tests and ship iterative improvements. • Build feedback loops (thumbs-up/down, rationale capture, escalation) and human-in-the-loop fallbacks that protect quality. • Own reliability and UX details that matter for customers: latency budgets, safe fallbacks, clear handoff to human agents, accessibility. • Partner with Trust/Legal/Security to ensure privacy-by-design and compliant data handling; implement guardrails and red-team mitigations.