Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
JeevesPosted 14 days ago

AI Engineer

Who we'd reach at JeevesFound and reached by Power Apply
Best leadEngineering manager

Leads the team you would join

Tech lead

Leads the work day to day

Technical recruiter

Owns the opening

Power Apply

From your own Gmail and LinkedIn.

How this role compares

One of 19 open AI Engineer roles in IN we are tracking today.

Posted 14 days ago, with 15 of the others posted since and 3 still open from before.

Counted across the roles Frontrunner has open right now.

About the role

This is a mid-level remote AI engineering role open only to candidates based in India, at Jeeves. The job is to build and run production AI features for Jeeves's financial platform, including LLM pipelines, retrieval systems, model serving and AI observability. Jeeves is a stablecoin-native banking platform for global businesses, with corporate cards, payments and treasury products across many countries.

What you’ll do

  • Design and maintain production LLM pipelines, including retrieval-augmented generation, prompts and output parsing.
  • Build AI features for spend categorisation, document extraction, anomaly detection, financial Q and A and reconciliation.
  • Add structured output validation, fallback handling and confidence scoring.
  • Build vector search and document ingestion for invoices, receipts, policies and transaction records.
  • Take trained models into production serving with latency targets and drift monitoring.
  • Integrate AI services into backend microservices with clear API contracts and graceful degradation.
  • Build human review flows for high-value financial decisions.
  • Set up logging, tracing and dashboards for AI systems.

What they’re looking for

  • A bachelor's degree in computer science or engineering, or equivalent practical experience.
  • Five or more years of software engineering, with at least three years on AI or machine learning systems in production.
  • Hands-on experience deploying LLM applications through APIs such as OpenAI, Anthropic or Cohere.
  • Experience with RAG pipelines, chunking, embeddings and vector databases.
  • Strong Python, plus familiarity with LangChain, LlamaIndex or similar.
  • Experience with model serving endpoints, input and output validation and monitoring.
  • Solid backend fundamentals, including REST APIs, PostgreSQL, async patterns and a major cloud provider.

Nice to have

  • Fintech or other regulated industry experience.
  • Prompt evaluation and model performance tracking in production.
  • MLflow, Weights and Biases, Vertex AI or SageMaker experience.
  • Kafka or Kinesis streaming experience.
  • Open-source, writing or conference contributions.
  • Startup or scale-up experience.

What’s on offer

  • Remote working, open to candidates based in India only.
  • The posting does not state salary.

Skills

Questions about this role

Is this role remote?

Yes, and it is open to candidates based in India only.

How many years of experience are required?

Five or more years of software engineering, with at least three years on production AI or machine learning systems.

Is salary stated?

The posting does not state a salary.