Bangalore, Karnataka · hace 4 meses
Construirás y depurarás servicios en Python y flujos de GenAI con LangChain y OpenAI, incluyendo recuperación basada en PGVector y marcos de evaluación para pipelines de LLM. También apoyarás despliegues del producto y análisis de causa raíz.
Hello there! Infrrd here. Haven’t heard of us before? No problem. First off, it’s pronounced In-fur-d. We are the creators of a proprietary Intelligent Document Processing platform that automates data extraction from complex and messy unstructured documents. For over a decade, we’ve been building expertise in Artificial Intelligence, Machine Learning, Deep Learning, Natural Language Processing, Neural Networks and much more. We are building technology that is disrupting the data extraction space for more than a decade now. And now, we are on the lookout for a motivated Python Developer to join our Engineering team. In this role, you will help us to build our product in an efficient and solid way. Job Purpose To provide hands-on technical support during implementation of Product features with a focus on rapid debugging, scripting, and data analysis; ensure smooth integrations and reliable deployments while improving developer productivity using AI-first tools and automation; and optimize the existing code and framework. Job Duties and Responsibilities • Build and debug features for the Product. Rollout issues across APIs, data transformations, and deployment workflows with rapid turnarounds. • Build and maintain Python utilities/services for validation, transformation, and automation of QC checklist execution. • Implement GenAI workflows using LangChain/OpenAI, including prompt design, tools, and guards for reliability and traceability. • Design and tune vector indexing and retrieval over PGVector for checklist content, policies, and artifacts. • Create evaluators, test harnesses, and regression suites for LLM pipelines and generated code outputs. • Instrument logs/metrics and perform root-cause analysis across data, prompts, and model outputs; document playbooks. • Collaborate with Product/CS/QA to triage tickets, reproduce issues, and ship hotfixes and safe migrations. • Harden deployments with config management, secrets hygiene, and rollback strategies for onboarding and production. • Maintain knowledge base and SOPs for integrations, data contracts, and compliance-sensitive workflows. Required Qualifications: • 4-6 years experience of strong Python development background • Bachelor's in CS/Engineering or equivalent practical experience • Experience implementing GenAI/LLM solutions in production-like settings • Excellent debugging and communication skills. Must-have Skills: • Python 3.x with strong software engineering and debugging proficiency. • GenAI/LLM: LangChain, OpenAI API, prompt engineering, tool/function calling, guards. • NLP utilities and text processing with nltk or similar. • MongoDB data modeling and query optimization for app/ops flows. • Vector databases and retrieval (PGVector on Postgres) for RAG-like patterns. • Observability and log analysis for rapid root-cause and fix-forward. • LLM orchestration with OpenAI/Gemini, including retries, timeouts, and structured outputs. • Vector retrieval with PGVector (indexing, chunking, similarity tuning, evals). • Debugging onboarding/deployment issues across configs, data, and environments Nice to have skills: • MLOps fundamentals (model/config/versioning, evals, CI for LLM flows). • MCP server or tool-agent patterns for internal developer workflows. • FastAPI/async IO for lightweight services and integrations. • CI/CD (GitHub Actions) and infra basics (Docker). • Experience with mortgage/QC/RegTech domains or checklists. • Python packaging, environments, and testing; REST APIs and JSON. • Prompt engineering basics; model limits, latency, and cost tradeoffs. • Data handling with Pandas and text normalization/tokenization Working Knowledge (Tools): • GitHub/Git; Issues/Projects; PR reviews. • JIRA/Confluence for triage and runbooks. • Postman/cURL for API validation. • VS Code with Copilot/Cursor; Python tooling (venv/poetry/pytest). By submitting your application, you agree that your personal information and resume may be collected, processed, and stored by us for recruitment purposes, including consideration for future roles.
Publicada el 5 jul 2026
