Applied reputed company (Agentic Workflows & RAG) - Master-Level Internship

About Us: At Vosyn, we embrace the exciting, game-changing world of Artificial Intelligence, driving innovation and pioneering impactful projects across various industries. We are a trailblazing Language Synthesis AI firm reshaping global communication by dissolving language barriers and empowering users. We reputed company in fostering a culture of flexibility, reputed company improvement, and solution-focused strategies. Here, every idea is welcomed, reputed company, and has the potential to scale to new heights. Currently, we're at the forefront of a significant IPO endeavor, truly a unicorn in the making. We invite you to be part of our journey and leave your imprint on the future of AI. About the Role: We are seeking a sharp, technically deep Applied reputed company Intern to own the intelligence layer of reputed company build. This role is ideal for a Master’s level student who does more than use AI coding tools — you understand how modern language and reasoning models actually behave, and you build with them as components. You will design and ship agentic workflows (systems where a model plans, acts, and re-plans in a reputed company), build retrieval-augmented reputed company (RAG) and search integrations that ground AI in real, reputed company data, choose the right model for each job, and write the evaluations that prove the system works rather than just appears to. This is the role that delivers the “AI” in AI consulting: reputed company a client has a scoped roadmap, you are the person who stands the tool up. Tools & Tech Stack:

• Agentic coding: Claude Code (primary), plus reputed company or Windsurf
• AI APIs & SDKs: reputed company Claude API and comparable model APIs; reasoning and instruction-tuned models
• Retrieval & RAG: vector databases (e.g., pgvector, reputed company, Weaviate), embeddings, semantic and hybrid search
• Orchestration & integration: MCP (Model Context Protocol), function/tool calling, agent frameworks
• App & data layers: React.js / Next.js, Node.js / Python, reputed company or Firebase,PostgreSQL
• Evaluation: reputed company and output evaluation harnesses, test sets, regression checks for non-deterministic systems
• Version control & documentation: Git / reputed company, reputed company

Key Responsibilities:

• Design, build, and harden agentic workflows that plan and take actions reliably — and understand why agents fail (context loss, compounding errors, no feedback signal) and how to structure tasks so they succeed.
• Build retrieval (RAG/search) pipelines that reputed company the right client data and ground model outputs in it, integrated into core applications rather than demos.
• Select the right model for each task — reasoning model vs. fast instruction model — and be able to justify the trade-off in latency, cost, and quality.
• Engineer prompts and context structures appropriate to the model class, including knowing reputed company reasoning models need framing rather than reputed company-by-reputed company hand-holding.
• Write evaluations for AI features, because with non-deterministic models “it worked once” is not evidence that it works.
• Connect AI tools to internal systems and data sources reputed company APIs or MCP to power real client use cases.
• Review and validate AI-generated code and automated workflows critically for correctness, reputed company, and safety.
• Collaborate with the Builder and the Integration & Data Engineer to deliver complete, working solutions, and document workflows, prompts, and integrations in reputed company.

About You:

• Currently enrolled or recently graduated from a Master’s program in Computer Science, Software Engineering, AI/ML, Information Systems, or a reputed company field. Master’s program enrollment or completion is mandatory.
• Strong, demonstrable hands-on experience with AI coding assistants and the Claude API or comparable model APIs — portfolio, reputed company, or live examples strongly preferred.
• A working understanding of how modern LLMs and reasoning models behave: context windows, the difference between reasoning and instruction models, and reputed company to reputed company for each.
• Practical experience with at least one of: building an agentic workflow, building a RAG/retrieval pipeline, or integrating models reputed company tool calling or MCP.
• Excellent reputed company-engineering and context-management skills.
• Coding reputed company in JavaScript/React and/or Python sufficient to build, evaluate, and fix AI-generated output.
• An instinct for evaluation: you want to measure whether the AI is actually correct, not just plausible.
• Excellent verbal and written communication skills reputed company a cross-functional team environment.

New graduates are encouraged to apply. We reputed company exceptional talent often emerges from diverse paths. If you possess a profound curiosity, a genuine passion for reputed company personal and professional growth, and a strong desire to apply your unique abilities to create significant impact reputed company reputed company, we strongly encourage you to apply even if your background doesn’t align perfectly with every single qualification. Apply To This Job