Research Intern - ML

Infrrd Inc.; Bengaluru; On-site; INR 167,000 - 279,000; Full time

Job summary

Infrrd Inc. is seeking a Research Intern to contribute to experiments shaping our enterprise document AI offerings. You will work under senior researchers on agentic extraction, LLM‑based auditing of mortgage documents, and calibrated table extraction with trust scores.

This hands‑on role includes data preparation, prototype building, error reasoning, and reproducible reporting. The role targets 2027 graduates with strong Python skills, ML/NLP knowledge, and a passion for rigorous

Qualifications

• Strong mathematical and statistical foundation with grasp of core ML concepts.
• Academic or project experience in NLP, computer vision, or document understanding (OCR, layout, tables, forms).
• Ability to run experiments scientifically and communicate outcomes clearly.

Responsibilities

• Experimentation and Prototyping: design and run experiments to validate document processing and agentic extraction; build prototypes using LLM and vision‑language models APIs.
• Evaluation and Verification: build evaluation harnesses and verifier checks to measure trust in extractions and audits.
• Error and Trace Analysis: analyze model outputs and reasoning traces to identify failure modes and propose fixes.
• Data Quality and EDA: verify dataset quality and perform exploratory analysis on document characteristics.
• Rule and Checklist Work: convert domain rules into executable checks and measure precision/recall on documents.
• Literature Tracking: read and summarise recent papers on document AI and evaluation; present findings.
• Tooling and Workflow: use AI coding assistants and Jira; participate in stand‑ups and code reviews.
• Documentation and Communication: document methodology and results for reproducibility and internal reports.

Skills

Python

ML fundamentals

NLP

Transformer models

Data analysis

Education

BE/BTech/MTech in CS/related fields

Tools

Pytorch

LLM APIs

Job description

About Infrrd

Infrrd (pronounced In-fur-d) is an Enterprise AI company that automates document-heavy workflows for customers in mortgage, insurance, and finance. Our Research team works on the next generation of document intelligence: agentic systems that read, reason over, and audit complex documents with outputs that can be trusted and verified. We are looking for a Research Intern to join the team and contribute to experiments that shape what we ship.

About the Role

As a Research Intern, you will work on well-scoped research tasks under the guidance of senior researchers, across areas such as agentic document extraction, LLM-based auditing of mortgage documents, table extraction with calibrated trust scores, and verifiable evaluation of model outputs without ground truth. You will run experiments end to end: preparing and checking data, building prototypes, analysing errors and reasoning traces, and writing up what you found. This is a hands‑on role for someone who enjoys rigorous experimentation and wants exposure to real enterprise-scale document AI problems.

Education details: 10+ 2/PUC mandatory (No Diploma), B.E/B.Tech/M.Tech students from all Computer Science related backgrounds with a focus on machine learning, NLP, or computer vision.

Year of Graduation: 2027

Percentage criteria: minimum 60% aggregate and higher throughoutacademics.

Internship duration: 1 year with an opportunity to convert to a full‑time role based on performance.

What You Will Do

• Experimentation and Prototyping: Design and run experiments to validate document processing and agentic extraction approaches; build prototypes and proof‑of‑concept implementations using LLM and vision‑language model APIs.
• Evaluation and Verification: Help build evaluation harnesses and verifier checks (cross‑field consistency, structural invariants, multi‑pass agreement) that measure whether an extraction or audit verdict can be trusted, including when no ground truth is available.
• Error and Trace Analysis: Conduct in‑depth error analysis on model outputs and agent reasoning traces to identify failure modes, categorise them, and propose fixes.
• Data Quality and EDA: Verify the quality of datasets and synthetic document packages used in experiments; perform exploratory analysis to understand document characteristics and edge cases.
• Rule and Checklist Work: Assist in converting domain checklist rules into executable, testable checks and in measuring their precision and recall on real documents.
• Literature Tracking: Read and summarise recent papers on document AI, agent harnesses, RL post‑training, and evaluation; present findings in internal paper discussions.
• Tooling and Workflow: Use AI coding assistants (Claude Code, Copilot, or similar) and internal tools effectively; track progress in Jira; participate actively in stand‑ups and code reviews.
• Documentation and Communication: Document methodology, experiment setup, and results clearly so they are reproducible; contribute to technical reports, Confluence pages, and internal presentations.

Who You Are

• Strong mathematical, statistical, and probabilistic foundation with a solid grasp of core ML concepts.
• Strong Python skills, including writing clean, testable code within a larger codebase.
• Working knowledge of Transformer‑based language models and how to use LLM APIs (prompting, structured outputs, tool or function calling).
• Familiarity with evaluation methodology: designing metrics, building test sets, and analysing results with rigour rather than anecdotes.
• Academic or project experience in NLP, computer vision, or document understanding (OCR, layout, tables, forms).
• Ability to run experiments scientifically, keep track of what was tried, and communicate outcomes clearly.
• Curiosity about agentic systems and initiative in learning new techniques and applying them to real problems.

Good to Have

• Experience with vision‑language models or document‑specific models for extraction and layout understanding.
• Exposure to agent frameworks, multi‑agent orchestration, or harness design for LLM‑based systems.
• Familiarity with RL post‑training methods (GRPO, RLVR) or model fine‑tuning.
• Experience with table extraction, PDF parsing, or synthetic data generation.
• Contributions to open source, published work, or a portfolio of research projects.

Pay Stubs Data Extraction

NLP‑powered Table Extraction for Insurance Policy Data

Ally | Agentic AI for Mortgage

Automated Data Extraction from Engineering & Construction Drawings