Key Responsibilities

- LLM Integration & Evaluation: Assist in evaluating and benchmarking large language models (OpenAI GPT-4o, Anthropic Claude, Google Gemini) for accuracy, latency, and cost-efficiency.
- Context & Resource Optimization: Support development of techniques to manage context windows, optimize prompt design, and reduce token usage across multi-turn agent sessions.
- Agent Reliability & Testing: Help test and refine agent reasoning loops (ReAct), tool calling accuracy, and anti-hallucination guardrails.
- RAG & Search Benchmarking: Assist in testing and evaluating retrieval-augmented generation (RAG) pipelines, vector search accuracy, and document chunking strategies.
- Multi-Agent & Workflow Experiments: Support experimental features around multi-agent team workflows, task decomposition, and human-in-the-loop (HITL) approval gates.
- Clean Code & Test Coverage: Write clean, documented Python code and contribute unit/integration tests for AI-related components.
- Research & Technical Insights: Stay up to date with up-to-date advancements in agentic AI, MCP (Model Context Protocol), and LLM tooling, and summarize trade-offs for internal engineering use.

Qualifications




- Currently pursuing or recently completed a Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
- Solid programming skills in Python.
- Fundamental understanding of core LLM concepts — tokens, context windows, prompt engineering, embeddings, and API integration.
- Strong interest in applied AI systems, autonomous agents, and building real-world AI products.
- Eagerness to learn, experiment, and collaborate in a fast-paced environment.

Nice to Have
- Hands-on experience with LLM APIs (OpenAI, Anthropic Claude, Google Gemini).
- Exposure to vector databases (Qdrant, pgvector, Pinecone, Weaviate) or embedding frameworks (fastembed, SentenceTransformers).
- Familiarity with modern Python backend frameworks (FastAPI) or task queues (Celery / Redis).
- Prior side projects building AI chatbots, autonomous agents, RAG applications, or tool-using LLMs.

What You Will Gain
- Direct hands-on experience building production-grade agentic AI systems.
- Mentorship from experienced engineers working on real-world multi-agent orchestration.

Pay: ₹5,000.00 - ₹10,000.00 per month

Perks

- Paid sick time
- Paid time off

Work Location: Remote

📌 AI/ML Intern (India)
🏢 Tungsten Technologies
📍 India