Location: New Delhi

WHAT YOU WILL DO

We are seeking a talented and driven AI Engineer to join our team, focusing on the design, development, and deployment of production-grade AI solutions for the insurance and healthcare industry. In this role, you will be instrumental in architecting LLM-powered applications, RAG pipelines, and AI agents that solve real business problems across claims, underwriting, and policy servicing, while making enterprise-grade deployment decisions and building the evals, guardrails, and monitoring needed to operate safely in a regulated environment.

Responsibilities:

- Work with business stakeholders to build production-ready AI solutions for insurance which solve real problems and impact business KPIs

- Architect and build LLM-powered applications, RAG pipelines, and AI agents for real business workflows (document summarization, claims triage, underwriting support, policy Q&A)

- Make enterprise-grade deployment decisions: cloud hosting, scalability, latency budgets, and cost optimization

- Build evals from day one - output validation, PII redaction, hallucination mitigation - given the regulated nature of the data involved

- Contribute reusable frameworks, internal tooling, and best practices that other teams can build on

- Set up monitoring for model performance, drift, and cost across deployed AI systems

- Mentor other engineers and help raise the bar on AI engineering practices across the organization.

REQUIREMENTS

Core engineering:

- 5+ years of software engineering experience, with a minimum of 1 year in AI engineering

- Strong Java knowledge is required.

- Track record of taking systems from prototype to production, not just POCs

- Comfort with cloud infrastructure, CI/CD, and standard production practices (monitoring, versioning, testing)

Applied AI (2+ years):

- Proven experience with at least one AI solution live in production - not just a demo

- Hands-on LLM integration experience (OpenAI, Azure OpenAI, Anthropic/Claude)

- Practical experience building RAG pipelines using frameworks like LangChain or LangGraph

- Working knowledge of MLOps practices: model monitoring, versioning, performance tuning

- Experience building AI agents and tool/API integrations

- Understanding of the production realities of LLM systems: guardrails, grounding, hallucination mitigation, cost and latency tradeoffs

Nice to have:

- Background in insurance or another regulated industry (HIPAA, claims, underwriting, compliance-heavy environments)

- Familiarity with enterprise platforms such as Salesforce, Applied Epic, or Duck Creek

- Experience with AI sandbox / experimentation environments

- Exposure to fine-tuning, voice AI, or multi-agent orchestration at scale

ABOUT RIA

RIA is a tech company that leverages cutting-edge technology to revolutionize the insurance and healthcare industry. RIA has operations in India and in the US.

At the core of its operations is the Symphony platform, a Vertical AI platform which can be used for customised decision-making, automation, and data orchestration across Insurance and Health products.

Symphony can support businesses with its microservices-based architecture and helps modernize and modularize the legacy system.

WHY JOIN US

We're building the foundation of our team right now, and are looking for ambitious team members to join us and increase with us. The work environment is fast-paced and you would make a clear impact!

You'll partner with a stellar leadership team from IIT Kanpur, Kellogg, MIT Sloan, IIT Guwahati, and the University of Michigan. The team has also worked at companies such as McKinsey, Goldman Sachs, Niva Bupa, Acko, Care, ICICI Prudential, etc.