4 months ago
Bengaluru, IndiaMid Level / Senior
Responsibilities
- Build and debug product features across APIs, data transformations, and deployment workflows.
- Develop and maintain Python utilities and services for validation, transformation, automation, and QC checklist execution.
- Implement GenAI workflows using LangChain and OpenAI, including prompt design, tool or function calling, and reliability guards.
- Design and tune PGVector indexing and retrieval for checklist content, policies, and artifacts.
- Create evaluators, test harnesses, and regression suites for LLM pipelines and generated code outputs.
- Instrument logs and metrics, perform root-cause analysis, and document operational playbooks.
- Collaborate with Product, Customer Success, and QA to triage tickets, reproduce issues, and ship hotfixes and safe migrations.
- Harden onboarding and production deployments through configuration management, secrets hygiene, and rollback strategies.
- Maintain knowledge bases and SOPs for integrations, data contracts, and compliance-sensitive workflows.
Requirements
- 4–6 years of strong Python development experience.
- Bachelor’s degree in Computer Science or Engineering, or equivalent practical experience.
- Experience implementing GenAI or LLM solutions in production-like settings.
- Strong Python 3.x software engineering, debugging, and communication skills.
- Experience with LangChain, OpenAI API, prompt engineering, tool or function calling, and reliability guards.
- Experience with NLP utilities and text processing using NLTK or similar tools.
- Experience with MongoDB data modeling and query optimization.
- Experience with vector databases, Postgres, PGVector, indexing, chunking, similarity tuning, and retrieval evaluation.
- Experience with OpenAI or Gemini orchestration, including retries, timeouts, and structured outputs.
- Understanding of observability, log analysis, deployment debugging, and root-cause investigation.
- Preferred experience with MLOps fundamentals, MCP servers or tool-agent patterns, FastAPI, asynchronous I/O, GitHub Actions, Docker, Python packaging, pytest, Pandas, and text normalization or tokenization.
- Experience with mortgage, QC, RegTech, checklist, integration, REST API, or JSON workflows is beneficial.
- Working knowledge of GitHub, Git, GitHub Issues and Projects, pull-request reviews, JIRA, Confluence, Postman, cURL, VS Code, Copilot, Cursor, venv, Poetry, and pytest.
Tech Stack
Categories
About Infrrd
Infrrd provides an AI platform for intelligent document processing, extracting and structuring data from complex, unstructured documents and automating end‑to‑end workflows for enterprises in insurance, mortgage, finance, and logistics. Its products combine OCR, machine learning, and LLM-based pipelines to handle invoices, contracts, forms, and engineering drawings at scale, offered as enterprise software and services. Founded in 2016 and headquartered in San Jose, the company is privately held and raised a seed round in 2019.