About the role
Responsibilities:
- Design, build, and optimize scalable AI agents, backend systems, and APIs for document processing, AI pipelines, and client-facing platforms.
- Collaborate with ML, product, and data teams to deploy LLM, NLP, fine-tuning-powered microservices, and AI agents.
- Build tools to structure unstructured data and enable downstream decisioning logic.
- Ensure high availability, security, and performance of core systems handling sensitive BFSI/healthcare data.
- Own modules end-to-end from ideation and MVPs to production rollout and monitoring.
Requirements:
- Have 1-4 years of AI engineering experience.
- Experience working with unstructured data, PDFs, or document-heavy applications.
- A product mindset and comfort shipping features that balance performance, usability, and scale.
- Exposure to GenAI / LLMs (even if through side projects or hacks).
- Comfort working in fast-paced, startup environments with cross-functional teams.
Tech Stack:
- Languages: Python, LangChain.
- AI Tooling: OpenAI APIs, OCR (Tesseract, AWS Textract).
- Infra: AWS, GCP, Docker, Kubernetes, PostgreSQL, Redis.
- Data and ML: Pandas, spaCy, LLMs (GPT, Claude), FinBERT, NLP, fine-tuning, and Gen AI.
- DevOps: GitHub Actions, CI/CD, Monitoring (Datadog/Grafana).