Machine Learning Internship

The role: You'll own a scoped piece of that: building agent workflows, wiring up retrieval, and working out why a run fell over at step four. Real work, shipped.

Not shadowing someone else's. Selected intern's day-to-day responsibilities include: 1. Build and serve agent workflows through FastAPI services. 2. Design and improve RAG pipelines: chunking, retrieval quality, grounding.

3. Build and integrate MCP servers so agents can reach tools and data. 4. Evaluate agent runs. Trace the failure, name the failure mode, and fix it. 5.

Tune cost and latency across the pipeline. What you'll need: 1. One hard requirement: Python with FastAPI. You've built and deployed APIs, not just run notebooks.

2. Retrieval: you've built a RAG pipeline end to end. Chunking, reranking, hybrid search. 3. Agents: LangChain, LangGraph, MCP, tool calling, anything where the model takes more than one step.

4. Vector DBs: LanceDB, Qdrant, or whatever you've actually run. 5. Fundamentals: Tokenization, context windows, sampling, attention, embeddings, how these models get trained.

Note: You pick up new tools fast. This space changes monthly, so how quickly you learn matters more than what you already know today. Do well and you'll get a pre-placement offer in month five, before the internship ends.

Who can apply: Only those candidates can apply who: • are available for the work from home job/internship • can start the work from home job/internship between 18th Sep'26 and 23rd Oct'26 • are available for duration of 6 months • have relevant skills and interests Stipend: INR₹ 9,999 - 10,000 /month Deadline: 2026-10-21 23:59:59 Other perks: Certificate, Letter of recommendation, Flexible work hours, 5 days a week Skills required: Python, Artificial intelligence, LangChain and LLM evaluation Other Requirements: • 1.

Candidates in their final year of BTech/MTech or any related field. • 2. Available to join immediately. • 3. Available for a period of 6 months. About Company: What we're building: Before the interview call, Bash AI researches the candidate and writes the question plan.

During the call, it sits beside the interviewer and suggests what to ask next. After the call, it checks every claimed skill against what was actually said and writes the report in under a minute.

Between rounds, it carries forward what's verified and what's still open. At the end, it ranks the finalists side by side, every mark cited. Underneath that sits a lot of agent work.

Rebuilding a candidate's history from a resume and scattered public sources. Generating 80 questions with ideal and weak answers for a role it has never seen.

Following a live transcript and deciding when to nudge the interviewer. Grading a claim against what was said, consistently enough that two runs agree.

Most of it is multi-step and tool-heavy, and it fails in ways a single LLM call never does.