Senior AI Engineer

Jeeves; India; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Jeeves is hiring for a full-time remote position in LLM & AI Pipeline Engineering. You will be responsible for designing and maintaining production-grade LLM integration pipelines and developing AI features for financial products. Candidates should have over 5 years of software engineering experience with a strong focus on AI/ML systems, proficiency in Python, and hands-on experience with LLM applications. The position offers a dynamic environment in the fintech industry with opportunities for growth and collaboration.

Qualifications

• 5+ years of professional software engineering experience, especially in AI/ML.
• Hands-on experience with LLM-powered applications and APIs.
• Experience in designing RAG pipelines.

Responsibilities

• Design and maintain LLM integration pipelines.
• Optimize vector search pipelines for financial data.
• Collaborate with data scientists for model serving.

Skills

Python

AI/ML Systems

RAG Pipelines

APIs (OpenAI, Anthropic)

Backend Engineering

Education

Bachelor's degree in Computer Science or related field

Tools

Pinecone

LangChain

AWS

Job description

Jeeves is a financial operating system that provides corporate cards, cross‑border payments, and spend management software within one unified platform. The company operates in over 20 countries and serves a diverse client base.

Jeeves is building AI into the core of its platform—from intelligent spend categorization and anomaly detection to LLM‑powered workflows that help finance teams move faster.

Location: This is a full‑time remote position.

What You'll Do

LLM & AI Pipeline Engineering

• Design, build, and maintain production‑grade LLM integration pipelines—including retrieval‑augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.
• Develop and operate AI features within Jeeves's core financial products: spend categorization, document extraction, anomaly detection, financial Q&A, and automated reconciliation.
• Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.
• Evaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.
• Establish prompt versioning and evaluation practices to keep AI outputs accurate and consistent as models and data evolve.

Retrieval & Vector Search

• Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG‑based features.
• Build document ingestion and chunking pipelines for Jeeves's financial data—processing invoices, receipts, policy documents, and transaction records.
• Optimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re‑ranking techniques.

ML Model Serving & Operations

• Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.
• Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.
• Implement model performance monitoring and data drift detection to ensure production models remain accurate over time.
• Support model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.

Backend Integration & Reliability

• Integrate AI services cleanly with Jeeves's backend microservices—designing clear API contracts, circuit breakers, and graceful degradation patterns.
• Write high‑quality, testable backend code in Python or Go/Node.js to power AI‑integrated features.
• Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.
• Build human‑in‑the‑loop review workflows for AI decisions that require oversight—particularly for high‑value financial actions.

Collaboration & Growth

• Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.
• Contribute to a culture of quality by writing design docs, reviewing peers' AI system designs, and sharing learnings openly.
• Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.

Requirements

Minimum Requirements

• Bachelor's degree in Computer Science, Engineering, or a related field—or equivalent practical experience.
• 5+ years of professional software engineering experience, with at least 3 years focused on AI/ML systems in production.
• Hands‑on experience building and deploying LLM‑powered applications using APIs such as OpenAI, Anthropic, or Cohere in a production environment.
• Experience designing and operating RAG pipelines, including chunking strategies, embedding models, and vector database integration (Pinecone, Weaviate, pgvector, or similar).
• Strong proficiency in Python for AI/ML workloads; familiarity with at least one AI orchestration framework (LangChain, LlamaIndex, or equivalent).
• Experience with ML model serving infrastructure: REST or gRPC inference endpoints, input/output validation, latency budgeting, and monitoring.
• Solid backend engineering fundamentals: REST APIs, relational databases (PostgreSQL preferred), async patterns, and cloud infrastructure (AWS, GCP, or Azure).
• Experience with observability tooling: structured logging, distributed tracing, and building dashboards for AI system health.

Preferred Qualifications

• Experience in fintech, financial services, or any regulated industry where AI reliability and auditability are critical.
• Familiarity with prompt evaluation frameworks, A/B testing AI outputs, and tracking model performance degradation in production.
• Experience with ML lifecycle management tools: MLflow, Weights & Biases, Vertex AI, or SageMaker.
• Knowledge of real‑time data streaming (Kafka, Kinesis) for event‑driven AI pipelines.
• Contributions to open‑source AI tooling, published technical writing, or talks at AI/ML conferences.
• Prior startup or scale‑up experience—comfortable with ambiguity and building foundational systems from scratch.