Intern - Machine Learning Engineer

Location: Chennai, India

Department: Product Engineering

Experience: 0 to 1 Year

• Proficiency in prompting techniques such as few-shot prompting, system prompts, structured outputs, role prompting, and reasoning-oriented prompts.
• Familiarity with recent model releases, capability shifts, and architectural developments.
• Ability to run inference on local LLMs using tools like Ollama, VLLM, or Hugging Face Transformers

• Moderate to strong understanding of RAG architecture, including chunking, embeddings, retrieval, reranking, and generation.

• Working knowledge of AI agents, tool use, and agent orchestration frameworks such as LangChain, LlamaIndex, AutoGen, or custom frameworks.
• Understanding of MCP (Model Context Protocol) and AI skills/tool design
• Transformer architecture basics — attention mechanism, encoder/decoder, positional encoding, embeddings

• Strong Python skills, including clean, idiomatic code, proper error handling, algorithm design, and type hints.
• Ability to work with structured outputs: JSON schema, Pydantic models, data validation patterns
• Flask API development: REST endpoints, request/response handling, middleware
• Fundamental understanding of API scaling, including async and sync patterns and basic load considerations.
• Version control proficiency: Git branching, PRs, commit hygiene, resolving conflicts

• Ability to independently navigate an existing, non-trivial codebase using AI-assisted tools (Cursor, Claude, ChatGPT, GitHub Copilot, etc.)
• Uses AI tools to boost velocity — but can reason through code independently and does not require AI to explain every line

• Rough working knowledge of image processing concepts: preprocessing, transformations, color spaces
• Familiarity with OCR tools and their practical limitations (Tesseract, Docling, AWS Textract, etc.).
• Basic awareness of object detection concepts (bounding boxes, YOLO-style models)

• Ability to articulate technical decisions clearly in review calls and project syncs without needing repeated prompting to explain reasoning.
• Comfortable discussing system design trade-offs and architecture choices with leads and peers
• Strong written communication for async updates, PRs, and documentation

• Docker: containerizing Python services, multi-stage builds, docker-compose for local stacks
• Deep RAG expertise: Graph RAG, hybrid retrieval, vector database internals (Pinecone, Weaviate, Qdrant, pgvector)
• Custom LLM agent design: memory management, multi-step reasoning, tool routing, state machines
• Agent observability: tracing, logging agent runs, dashboards (LangSmith, Phoenix, custom)
• LLM/VLM fine-tuning: PEFT methods (LoRA, QLoRA), GRPO, instruction tuning pipelines
• Frontend / UI basics: HTML/CSS/JS or Streamlit for internal tooling and demos
• Active participation in product and solution architecture discussions
• Awareness of the latest releases, frameworks, and modern technologies, with the ability to choose current, practical solutions instead of relying on outdated approaches.

• You will be assigned tasks and expected to drive them to completion with minimal hand-holding.
• You should be able to take a vague requirement, ask the right clarifying questions, and convert it into working code.

• We expect you to use AI tools to move faster; that is the right instinct.
• We do not expect you to rely on AI for tasks you should already understand, such as debugging your own logic, reading stack traces, or justifying architectural decisions.

• You should be able to absorb guidance from managers and tech leads and translate it into concrete action without repeated follow-up
• Keep feedback loops tight by flagging blockers early and communicating progress proactively.

• Our systems are client-facing, so code quality, correctness, and documentation matter.
• You will be expected to review your own work before pushing it, not just submit first drafts

• LLM-powered document intelligence pipelines (extraction, structuring, generation)
• RAG systems with multi-source retrieval, reranking, and structured output formatting
• AI agent workflows with tool use, memory, and multi-step orchestration
• Flask- or FastAPI-based APIs that wrap AI capabilities for client-facing deployment
• Local LLM inference setups and evaluation harnesses
• Prompt engineering, evaluation, and iterative system improvement
• Client-facing projects with real-world business impact
• No-code and low-code solution development for internal tools and product prototypes