Applied AI Engineer - LLM & AI Agents
Summary
Build and ship production-ready LLM applications and multi-agent AI systems that process large volumes of financial and legal documents, plus the backend services (TypeScript, GraphQL, PostgreSQL) and evaluation pipelines behind them. Requires 3+ years of software engineering with hands-on Python LLM/agent experience.
About the Role:
We are looking for an experienced Applied AI Engineer to build and deploy intelligent AI systems that solve complex business problems.
The role focuses on developing production-ready LLM applications and AI agents capable of processing large volumes of financial and legal documents, retrieving relevant information, and generating accurate, evidence-backed insights.
You will work across AI agent development, backend engineering and evaluation systems, taking ownership of features from initial design through production deployment.
Key Responsibilities:
- Design and develop LLM-powered applications and stateful, multi-agent workflows.
- Build AI agents that can process, analyse and reason across complex document collections.
- Work with LLMs, embeddings, retrieval systems and context management.
- Develop backend services, APIs and database integrations to support AI capabilities.
- Build evaluation frameworks, test datasets and feedback mechanisms to improve system accuracy.
- Monitor, debug and optimise AI systems running in production.
- Maintain traceability of AI outputs, tool calls and supporting evidence.
- Evaluate emerging AI models and techniques and integrate them where they improve product performance.
Mandatory Technical Requirements:
- Minimum 3 years of professional software engineering experience.
- Proven experience building and shipping LLM-based systems to production.
- Strong understanding of LLM architecture, embeddings and retrieval mechanisms.
- Hands-on experience with Python and AI agent development.
- Understanding of multi-agent workflows, tool calling, context and state management.
- Experience developing backend services, APIs and databases.
- Working knowledge of TypeScript, GraphQL and PostgreSQL.
- Experience building evaluation pipelines, automated testing and feedback loops.
- Previous experience in a product-based company is mandatory.
Good to Have:
- Experience handling scanned documents, OCR, long PDFs and complex tables.
- Exposure to financial, legal, lending or insurance documents.
- Experience with model fine-tuning techniques such as LoRA and RLHF/RLAIF.
- Experience with DSPy or graph-based data modelling.
Educational Qualification:
- Candidates with 5+ years of experience: B.Tech in any engineering branch.
- Candidates with 3 - 5 years of experience: B.Tech in Computer Science Engineering (CSE) only.
- Graduates from Tier-1 engineering colleges preferred.
Important Screening Criteria:
This role requires practical production experience with LLM-based systems. Candidates with only theoretical AI/ML knowledge, academic projects or basic chatbot development experience will not meet the core requirements.
Please apply only if you meet the mandatory experience, educational, technical and product-company criteria.